Daily Papers

With the rise of LLMs, a large number of Model Context Protocol (MCP) services have emerged since the end of 2024. However, the effectiveness and efficiency of MCP servers have not been well studied. To study these questions, we propose an evaluation framework, called MCPBench. We selected several widely used MCP server and conducted an experimental evaluation on their accuracy, time, and token usage. Our experiments showed that the most effective MCP, Bing Web Search, achieved an accuracy of 64%. Importantly, we found that the accuracy of MCP servers can be substantially enhanced by involving declarative interface. This research paves the way for further investigations into optimized MCP implementations, ultimately leading to better AI-driven applications and data retrieval solutions.

AI evaluation results are produced at scale but reported inconsistently across leaderboards, model cards, benchmark papers, and company blogs. The cost is interpretive: readers cannot reliably compare results across sources, identify what a report omits, or trace an aggregate claim to its underlying evidence. Recent efforts address isolated components but leave three gaps: they cover only narrow slices of the evaluation lifecycle and do not compose into a single interpretable record; they specify static representations that do not differentiate the questions different stakeholders bring to the same evidence; and they remain proposals on paper, lacking the extraction infrastructure required for adoption at scale. We present , an operational reporting layer that composes benchmark metadata, evaluation run data, and model metadata into a unified record. We (1) derive a reporting schema from a structured review of 52 papers and 10 stakeholder interviews, (2) implement four interpretive signals (reproducibility, documentation completeness, provenance and risk, and score comparability), rendered through reader modes calibrated to research and non-research audiences, and (3) deploy a monitoring tool that applies across 5,816 models, 635 benchmarks, and 101,843 results, surfacing systematic gaps in current reporting practice.

Benchmark suites assess model capability on controlled tasks; large-scale conversation corpora capture naturalistic use without user feedback; and in-interface feedback mechanisms record satisfaction without task purpose. Together, they leave a critical gap in LLM evaluation: no existing infrastructure routinely links interaction trajectories to user-defined outcomes. We introduce MonitrLLM, open-source infrastructure for community-centered LLM evaluations that links full conversation transcripts to user-reported task intent and outcome assessments, treating all three as primary evaluative signals rather than optional metadata. To demonstrate the value of this approach, we conducted a two-week feasibility pilot with 26 college students using ChatGPT, collecting 206 evaluation reports with full conversation transcripts. The findings from our pilot demonstrate the value of connecting conversation trajectories with user-reported outcomes. For instance, despite reporting high average satisfaction (4.19/5) with their LLM interactions, participants also experience a substantial 23.1% failure rate on their goal tasks. We also find that multi-turn conversations are reported as failing at 2.5 times the rate of single-turn exchanges, a pattern that reframes extended interaction as a signal of difficulty rather than engagement. We conclude by discussing the value of incorporating direct user feedback with observational data for robust LLM evaluations, and the possibilities for infrastructure that enables this goal.

Training large language models for complex reasoning is bottlenecked by the scarcity of verifiable, high-quality data. In domains like physics, standard text augmentation often introduces hallucinations, while static benchmarks lack the reasoning traces required for fine-tuning. We introduce the Infinite Problem Generator (IPG), an agentic framework that synthesizes physics problems with guaranteed solvability through a Formula-as-Code paradigm. Unlike probabilistic text generation, IPG constructs solutions as executable Python programs, enforcing strict mathematical consistency. As a proof-of-concept, we release ClassicalMechanicsV1, a high-fidelity corpus of 1,335 classical mechanics problems expanded from 165 expert seeds. The corpus demonstrates high structural diversity, spanning 102 unique physical formulas with an average complexity of 3.05 formulas per problem. Furthermore, we identify a Complexity Blueprint, demonstrating a strong linear correlation (R^2 approx 0.95) between formula count and verification code length. This relationship establishes code complexity as a precise, proxy-free metric for problem difficulty, enabling controllable curriculum generation. We release the full IPG pipeline, the ClassicalMechanicsV1 dataset, and our evaluation report to support reproducible research in reasoning-intensive domains.

Foundation models are increasingly central to high-stakes AI systems, and governance frameworks now depend on evaluations to assess their risks and capabilities. Although general capability evaluations are widespread, social impact assessments covering bias, fairness, privacy, environmental costs, and labor practices remain uneven across the AI ecosystem. To characterize this landscape, we conduct the first comprehensive analysis of both first-party and third-party social impact evaluation reporting across a wide range of model developers. Our study examines 186 first-party release reports and 183 post-release evaluation sources, and complements this quantitative analysis with interviews of model developers. We find a clear division of evaluation labor: first-party reporting is sparse, often superficial, and has declined over time in key areas such as environmental impact and bias, while third-party evaluators including academic researchers, nonprofits, and independent organizations provide broader and more rigorous coverage of bias, harmful content, and performance disparities. However, this complementarity has limits. Only model developers can authoritatively report on data provenance, content moderation labor, financial costs, and training infrastructure, yet interviews reveal that these disclosures are often deprioritized unless tied to product adoption or regulatory compliance. Our findings indicate that current evaluation practices leave major gaps in assessing AI's societal impacts, highlighting the urgent need for policies that promote developer transparency, strengthen independent evaluation ecosystems, and create shared infrastructure to aggregate and compare third-party evaluations in a consistent and accessible way.

In this work, we present a modular and interpretable framework that uses Large Language Models (LLMs) to automate candidate assessment in recruitment. The system integrates diverse sources, including job descriptions, CVs, interview transcripts, and HR feedback; to generate structured evaluation reports that mirror expert judgment. Unlike traditional ATS tools that rely on keyword matching or shallow scoring, our approach employs role-specific, LLM-generated rubrics and a multi-agent architecture to perform fine-grained, criteria-driven evaluations. The framework outputs detailed assessment reports, candidate comparisons, and ranked recommendations that are transparent, auditable, and suitable for real-world hiring workflows. Beyond rubric-based analysis, we introduce an LLM-Driven Active Listwise Tournament mechanism for candidate ranking. Instead of noisy pairwise comparisons or inconsistent independent scoring, the LLM ranks small candidate subsets (mini-tournaments), and these listwise permutations are aggregated using a Plackett-Luce model. An active-learning loop selects the most informative subsets, producing globally coherent and sample-efficient rankings. This adaptation of listwise LLM preference modeling (previously explored in financial asset ranking) provides a principled and highly interpretable methodology for large-scale candidate ranking in talent acquisition.

This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models. We introduce a principled approach to specifying and constructing the benchmark, which for v0.5 covers only a single use case (an adult chatting to a general-purpose assistant in English), and a limited set of personas (i.e., typical users, malicious users, and vulnerable users). We created a new taxonomy of 13 hazard categories, of which 7 have tests in the v0.5 benchmark. We plan to release version 1.0 of the AI Safety Benchmark by the end of 2024. The v1.0 benchmark will provide meaningful insights into the safety of AI systems. However, the v0.5 benchmark should not be used to assess the safety of AI systems. We have sought to fully document the limitations, flaws, and challenges of v0.5. This release of v0.5 of the AI Safety Benchmark includes (1) a principled approach to specifying and constructing the benchmark, which comprises use cases, types of systems under test (SUTs), language and context, personas, tests, and test items; (2) a taxonomy of 13 hazard categories with definitions and subcategories; (3) tests for seven of the hazard categories, each comprising a unique set of test items, i.e., prompts. There are 43,090 test items in total, which we created with templates; (4) a grading system for AI systems against the benchmark; (5) an openly available platform, and downloadable tool, called ModelBench that can be used to evaluate the safety of AI systems on the benchmark; (6) an example evaluation report which benchmarks the performance of over a dozen openly available chat-tuned language models; (7) a test specification for the benchmark.

Radiology report evaluation is essential for advancing automated report generation. Natural language generation metrics have limited clinical relevance. Clinical efficacy (CE) metrics evaluate important medical findings, but focus mainly on presence and cover only a limited set of entities. Due to heavy reliance on manual annotations, it is difficult for CE metrics to extend clinical entities or attributes. In clinical practice, radiology reports serve as a medium for information transfer. Clinicians use them to perform downstream diagnostic tasks without directly inspecting images. Based on this insight, we propose ReportQA, a clinical-related and flexible radiology report evaluation framework, supporting detailed quantitative analysis of radiology report generation systems. We first collect datasets covering multiple imaging modalities and anatomical regions. We then construct knowledge trees of clinical entities and attributes with radiologist guidance, and use large language models (LLMs) to extract structured information from raw reports. Next, we generate QA pairs from predefined templates and apply quality control through self-filtering and report-based filtering. During evaluation, the report is treated as context, and an LLM acts as a judge model to answer the QA pairs. Based on the resulting QA accuracy, we introduce QAScore metric. Compared with existing metrics, QAScore shows better alignment with radiologist judgments. Experiments on multiple state-of-the-art vision-language models reveal that current report-based inference paradigms struggle to learn fine-grained clinical representations and exhibit strong negative prior biases. In contrast, question-driven inference provides a more effective alternative. For reproducibility and extensibility, we release the knowledge trees, structured reports, and QA pairs, along with the pipeline code for QA construction and evaluation.

Evaluating radiology reports is a challenging problem as factual correctness is extremely important due to the need for accurate medical communication about medical images. Existing automatic evaluation metrics either suffer from failing to consider factual correctness (e.g., BLEU and ROUGE) or are limited in their interpretability (e.g., F1CheXpert and F1RadGraph). In this paper, we introduce GREEN (Generative Radiology Report Evaluation and Error Notation), a radiology report generation metric that leverages the natural language understanding of language models to identify and explain clinically significant errors in candidate reports, both quantitatively and qualitatively. Compared to current metrics, GREEN offers: 1) a score aligned with expert preferences, 2) human interpretable explanations of clinically significant errors, enabling feedback loops with end-users, and 3) a lightweight open-source method that reaches the performance of commercial counterparts. We validate our GREEN metric by comparing it to GPT-4, as well as to error counts of 6 experts and preferences of 2 experts. Our method demonstrates not only higher correlation with expert error counts, but simultaneously higher alignment with expert preferences when compared to previous approaches."

Radiological imaging is central to diagnosis, treatment planning, and clinical decision-making. Vision-language foundation models have spurred interest in automated radiology report generation (RRG), but safe deployment requires reliable clinical evaluation of generated reports. Existing metrics often rely on surface-level similarity or behave as black boxes, lacking interpretability. We introduce ICARE (Interpretable and Clinically-grounded Agent-based Report Evaluation), an interpretable evaluation framework leveraging large language model agents and dynamic multiple-choice question answering (MCQA). Two agents, each with either the ground-truth or generated report, generate clinically meaningful questions and quiz each other. Agreement on answers captures preservation and consistency of findings, serving as interpretable proxies for clinical precision and recall. By linking scores to question-answer pairs, ICARE enables transparent, and interpretable assessment. Clinician studies show ICARE aligns significantly more with expert judgment than prior metrics. Perturbation analyses confirm sensitivity to clinical content and reproducibility, while model comparisons reveal interpretable error patterns.

As AI systems are increasingly used to draft radiology reports, reliably evaluating their clinical quality remains a critical challenge. Large language model (LLM)-based metrics are now the best-correlated with radiologist judgment, yet they output a single opaque score that neither a clinician nor a model builder can easily interpret or audit. We introduce RadMatch, a multi-stage, LLM-based metric that decomposes report comparison into a structured finding-level matching with significance-aware scoring and error characterization across seven clinical attribute dimensions (status, location, severity, morphology, certainty, longitudinal comparison, and measurement). The main score is the actionable-error count, both interpretable and auditable. Candidate findings are graded correct, partial, or incorrect, and unmatched findings are counted as missed or hallucinated. Triage and actionable safety recall/precision and per-subset views add complementary, deployment-oriented lenses. Across two expert benchmarks, RadMatch is the most clinically aligned metric, matching inter-radiologist agreement on ReXVal and more than doubling the best prior metric on the harder RadEvalExpert. Relying only on few-shot prompting, it is designed to extend to other modalities and anatomies. We will release RadMatch as open-source code with an interactive dashboard for inspecting results.

Longitudinal information in radiology reports refers to the sequential tracking of findings across multiple examinations over time, which is crucial for monitoring disease progression and guiding clinical decisions. Many recent automated radiology report generation methods are designed to capture longitudinal information; however, validating their performance is challenging. There is no proper tool to consistently label temporal changes in both ground-truth and model-generated texts for meaningful comparisons. Large language models (LLMs) offer a promising annotation alternative, as they are capable of capturing nuanced linguistic patterns and semantic similarities without extensive manual intervention. They also adapt well to new contexts. In this study, we therefore propose an LLM-based pipeline to automatically annotate longitudinal information in radiology reports. The pipeline first identifies sentences containing relevant information and then extracts the progression of diseases. We evaluate and compare five mainstream LLMs on these two tasks using 500 manually annotated reports. Considering both efficiency and performance, Qwen2.5-32B was subsequently selected and used to annotate another 95,169 reports from the public MIMIC-CXR dataset. Our Qwen2.5-32B-annotated dataset provided us with a standardized benchmark for evaluating report generation models. Using this new benchmark, we assessed seven state-of-the-art report generation models. Our LLM-based annotation method outperforms existing annotation solutions, achieving 11.3\% and 5.3\% higher F1-scores for longitudinal information detection and disease tracking, respectively. The source code is available at https://github.com/wxinyi1996/Standardizing-Longitudinal-Chest-X-ray-Report-Evaluation-via-Large-Language-Model-Annotation.git.

Automatic medical report generation supports clinical diagnosis, reduces the workload of radiologists, and holds the promise of improving diagnosis consistency. However, existing evaluation metrics primarily assess the accuracy of key medical information coverage in generated reports compared to human-written reports, while overlooking crucial details such as the location and certainty of reported abnormalities. These limitations hinder the comprehensive assessment of the reliability of generated reports and pose risks in their selection for clinical use. Therefore, we propose a Granular Explainable Multi-Agent Score (GEMA-Score) in this paper, which conducts both objective quantification and subjective evaluation through a large language model-based multi-agent workflow. Our GEMA-Score parses structured reports and employs NER-F1 calculations through interactive exchanges of information among agents to assess disease diagnosis, location, severity, and uncertainty. Additionally, an LLM-based scoring agent evaluates completeness, readability, and clinical terminology while providing explanatory feedback. Extensive experiments validate that GEMA-Score achieves the highest correlation with human expert evaluations on a public dataset, demonstrating its effectiveness in clinical scoring (Kendall coefficient = 0.70 for Rexval dataset and Kendall coefficient = 0.54 for RadEvalX dataset). The anonymous project demo is available at: https://github.com/Zhenxuan-Zhang/GEMA_score.

Medical domain automated text generation is an active area of research and development; however, evaluating the clinical quality of generated reports remains a challenge, especially in instances where domain-specific metrics are lacking, e.g. histopathology. We propose HARE (Histopathology Automated Report Evaluation), a novel entity and relation centric framework, composed of a benchmark dataset, a named entity recognition (NER) model, a relation extraction (RE) model, and a novel metric, which prioritizes clinically relevant content by aligning critical histopathology entities and relations between reference and generated reports. To develop the HARE benchmark, we annotated 813 de-identified clinical diagnostic histopathology reports and 652 histopathology reports from The Cancer Genome Atlas (TCGA) with domain-specific entities and relations. We fine-tuned GatorTronS, a domain-adapted language model to develop HARE-NER and HARE-RE which achieved the highest overall F1-score (0.915) among the tested models. The proposed HARE metric outperformed traditional metrics including ROUGE and Meteor, as well as radiology metrics such as RadGraph-XL, with the highest correlation and the best regression to expert evaluations (higher than the second best method, GREEN, a large language model based radiology report evaluator, by Pearson r = 0.168, Spearman ρ= 0.161, Kendall τ= 0.123, R^2 = 0.176, RMSE = 0.018). We release HARE, datasets, and the models at https://github.com/knowlab/HARE to foster advancements in histopathology report generation, providing a robust framework for improving the quality of reports.

Traditional metrics for Medical Report Generation (MRG) predominantly rely on surface-level n-gram overlap, which fails to capture clinical factual accuracy and often overlooks catastrophic diagnostic errors. We address this fundamental limitation by proposing AtomiMed, a universal, modality-agnostic evaluation framework that decomposes complex medical narratives into a standardized, multi-level hierarchy of Atomic Clinical Facts, encompassing Disease-level entities and Attribute-level descriptors, including location, morphology, and severity. By implementing an Agentic Cross-Verification loop between ground-truth and predicted reports, AtomiMed simulates a multi-radiologist peer-review process to verify clinical consistency, thus enabling the decoupled assessment of diagnostic detection and descriptive accuracy. To facilitate standardized evaluation, we introduce MRGEvalKit, an open-source toolkit for automated hierarchical extraction, and curate OmniMRG-Bench, a comprehensive multi-modal benchmark covering X-ray, CT, MRI, and Ultrasound. Extensive experiments on multiple expert-annotated reader studies demonstrate that AtomiMed achieves significantly higher correlation with human radiologist judgment compared to traditional and model-based metrics. Our code are release at https://github.com/Venn2336/MRGEvalkit

This paper explores the use of Large Language Models (LLMs) in the generation and evaluation of analytical reports derived from Earnings Calls (ECs). Addressing a current gap in research, we explore the generation of analytical reports with LLMs in a multi-agent framework, designing specialized agents that introduce diverse viewpoints and desirable topics of analysis into the report generation process. Through multiple analyses, we examine the alignment between generated and human-written reports and the impact of both individual and collective agents. Our findings suggest that the introduction of additional agents results in more insightful reports, although reports generated by human experts remain preferred in the majority of cases. Finally, we address the challenging issue of report evaluation, we examine the limitations and strengths of LLMs in assessing the quality of generated reports in different settings, revealing a significant correlation with human experts across multiple dimensions.

As intelligent agents become more generally-capable, i.e. able to master a wide variety of tasks, the complexity and cost of properly evaluating them rises significantly. Tasks that assess specific capabilities of the agents can be correlated and stochastic, requiring many samples for accurate comparisons, leading to added costs. In this paper, we propose a formal definition and a conceptual framework for active evaluation of agents across multiple tasks, which assesses the performance of ranking algorithms as a function of number of evaluation data samples. Rather than curating, filtering, or compressing existing data sets as a preprocessing step, we propose an online framing: on every iteration, the ranking algorithm chooses the task and agents to sample scores from. Then, evaluation algorithms report a ranking of agents on each iteration and their performance is assessed with respect to the ground truth ranking over time. Several baselines are compared under different experimental contexts, with synthetic generated data and simulated online access to real evaluation data from Atari game-playing agents. We find that the classical Elo rating system -- while it suffers from well-known failure modes, in theory -- is a consistently reliable choice for efficient reduction of ranking error in practice. A recently-proposed method, Soft Condorcet Optimization, shows comparable performance to Elo on synthetic data and significantly outperforms Elo on real Atari agent evaluation. When task variation from the ground truth is high, selecting tasks based on proportional representation leads to higher rate of ranking error reduction.

The widespread deployment of general-purpose AI (GPAI) systems introduces significant new risks. Yet the infrastructure, practices, and norms for reporting flaws in GPAI systems remain seriously underdeveloped, lagging far behind more established fields like software security. Based on a collaboration between experts from the fields of software security, machine learning, law, social science, and policy, we identify key gaps in the evaluation and reporting of flaws in GPAI systems. We call for three interventions to advance system safety. First, we propose using standardized AI flaw reports and rules of engagement for researchers in order to ease the process of submitting, reproducing, and triaging flaws in GPAI systems. Second, we propose GPAI system providers adopt broadly-scoped flaw disclosure programs, borrowing from bug bounties, with legal safe harbors to protect researchers. Third, we advocate for the development of improved infrastructure to coordinate distribution of flaw reports across the many stakeholders who may be impacted. These interventions are increasingly urgent, as evidenced by the prevalence of jailbreaks and other flaws that can transfer across different providers' GPAI systems. By promoting robust reporting and coordination in the AI ecosystem, these proposals could significantly improve the safety, security, and accountability of GPAI systems.

In this paper, we compare the performance of using binaural audio features in place of single-channel features for sound event detection. Three different binaural features are studied and evaluated on the publicly available TUT Sound Events 2017 dataset of length 70 minutes. Sound event detection is performed separately with single-channel and binaural features using stacked convolutional and recurrent neural network and the evaluation is reported using standard metrics of error rate and F-score. The studied binaural features are seen to consistently perform equal to or better than the single-channel features with respect to error rate metric.

The 1st Workshop on Data Contamination (CONDA 2024) focuses on all relevant aspects of data contamination in natural language processing, where data contamination is understood as situations where evaluation data is included in pre-training corpora used to train large scale models, compromising evaluation results. The workshop fostered a shared task to collect evidence on data contamination in current available datasets and models. The goal of the shared task and associated database is to assist the community in understanding the extent of the problem and to assist researchers in avoiding reporting evaluation results on known contaminated resources. The shared task provides a structured, centralized public database for the collection of contamination evidence, open to contributions from the community via GitHub pool requests. This first compilation paper is based on 566 reported entries over 91 contaminated sources from a total of 23 contributors. The details of the individual contamination events are available in the platform. The platform continues to be online, open to contributions from the community.

In recent years, automated radiology report generation has experienced significant growth. This paper introduces MRScore, an automatic evaluation metric tailored for radiology report generation by leveraging Large Language Models (LLMs). Conventional NLG (natural language generation) metrics like BLEU are inadequate for accurately assessing the generated radiology reports, as systematically demonstrated by our observations within this paper. To address this challenge, we collaborated with radiologists to develop a framework that guides LLMs for radiology report evaluation, ensuring alignment with human analysis. Our framework includes two key components: i) utilizing GPT to generate large amounts of training data, i.e., reports with different qualities, and ii) pairing GPT-generated reports as accepted and rejected samples and training LLMs to produce MRScore as the model reward. Our experiments demonstrate MRScore's higher correlation with human judgments and superior performance in model selection compared to traditional metrics. Our code and datasets will be available on GitHub.

Epilepsy is a common disease of the nervous system. Timely prediction of seizures and intervention treatment can significantly reduce the accidental injury of patients and protect the life and health of patients. This paper presents a neuromorphic Spiking Convolutional Transformer, named Spiking Conformer, to detect and predict epileptic seizure segments from scalped long-term electroencephalogram (EEG) recordings. We report evaluation results from the Spiking Conformer model using the Boston Children's Hospital-MIT (CHB-MIT) EEG dataset. By leveraging spike-based addition operations, the Spiking Conformer significantly reduces the classification computational cost compared to the non-spiking model. Additionally, we introduce an approximate spiking neuron layer to further reduce spike-triggered neuron updates by nearly 38% without sacrificing accuracy. Using raw EEG data as input, the proposed Spiking Conformer achieved an average sensitivity rate of 94.9% and a specificity rate of 99.3% for the seizure detection task, and 96.8%, 89.5% for the seizure prediction task, and needs >10x fewer operations compared to the non-spiking equivalent model.

Previous literature has largely shown that Large Language Models (LLMs) perpetuate social biases learnt from their pre-training data. Given the notable lack of resources for social bias evaluation in languages other than English, and for social contexts outside of the United States, this paper introduces the Spanish and the Catalan Bias Benchmarks for Question Answering (EsBBQ and CaBBQ). Based on the original BBQ, these two parallel datasets are designed to assess social bias across 10 categories using a multiple-choice QA setting, now adapted to the Spanish and Catalan languages and to the social context of Spain. We report evaluation results on different LLMs, factoring in model family, size and variant. Our results show that models tend to fail to choose the correct answer in ambiguous scenarios, and that high QA accuracy often correlates with greater reliance on social biases.

Ontology Matching (OM) plays an important role in many domains such as bioinformatics and the Semantic Web, and its research is becoming increasingly popular, especially with the application of machine learning (ML) techniques. Although the Ontology Alignment Evaluation Initiative (OAEI) represents an impressive effort for the systematic evaluation of OM systems, it still suffers from several limitations including limited evaluation of subsumption mappings, suboptimal reference mappings, and limited support for the evaluation of ML-based systems. To tackle these limitations, we introduce five new biomedical OM tasks involving ontologies extracted from Mondo and UMLS. Each task includes both equivalence and subsumption matching; the quality of reference mappings is ensured by human curation, ontology pruning, etc.; and a comprehensive evaluation framework is proposed to measure OM performance from various perspectives for both ML-based and non-ML-based OM systems. We report evaluation results for OM systems of different types to demonstrate the usage of these resources, all of which are publicly available as part of the new BioML track at OAEI 2022.

In this study, we tackle a growing concern around the safety and ethical use of large language models (LLMs). Despite their potential, these models can be tricked into producing harmful or unethical content through various sophisticated methods, including 'jailbreaking' techniques and targeted manipulation. Our work zeroes in on a specific issue: to what extent LLMs can be led astray by asking them to generate responses that are instruction-centric such as a pseudocode, a program or a software snippet as opposed to vanilla text. To investigate this question, we introduce TechHazardQA, a dataset containing complex queries which should be answered in both text and instruction-centric formats (e.g., pseudocodes), aimed at identifying triggers for unethical responses. We query a series of LLMs -- Llama-2-13b, Llama-2-7b, Mistral-V2 and Mistral 8X7B -- and ask them to generate both text and instruction-centric responses. For evaluation we report the harmfulness score metric as well as judgements from GPT-4 and humans. Overall, we observe that asking LLMs to produce instruction-centric responses enhances the unethical response generation by ~2-38% across the models. As an additional objective, we investigate the impact of model editing using the ROME technique, which further increases the propensity for generating undesirable content. In particular, asking edited LLMs to generate instruction-centric responses further increases the unethical response generation by ~3-16% across the different models.

Large language models (LLMs) deployed for logical reasoning in knowledge-intensive domains exhibit a subtle but critical failure: coherence can be vacuously achieved through systematic abstention. A model that withholds commitment to either entailment or refutation satisfies negation consistency while providing no utility. We introduce Coherence Under Commitment (CUC), a dual-query evaluation paradigm that jointly measures consistency and decisiveness. CUC contributes three innovations: (1) a commitment score c(φ) = p(φ) + p(lnotφ) quantifying probability mass allocated to decisive outcomes; (2) a deterministic elicitation protocol via normalized YES/NO log probabilities, eliminating sampling variance; and (3) a 3-way decision framework (True/False/Uncertain) operationalizing the coherence-commitment trade-off into metrics. Experiments on four open-weight LLMs (1B-3B) across 204 FOLIO examples expose a sharp frontier. Qwen2.5-3B achieves near-zero contradiction (E[v_{neg}]{=}0.025) but only 7.4% coverage, while TinyLlama-1.1B reaches 79.4% coverage with violations on every example. Coherence-only evaluation would rank the abstaining model first; CUC exposes this as vacuous, and the frontier generalizes to LogiQA~v2 (ρ{=}0.97). We argue that evaluation must report both coherence and non-vacuous commitment and release a toolkit for standardized assessment.

Enterprise agents increasingly operate inside workspaces: they read heterogeneous files, invoke tools, and deliver business artifacts. We introduce EnterpriseClawBench, an enterprise agent benchmark constructed from proprietary, real-world agent sessions. Starting from a large archive of workplace sessions, the EnterpriseClawBench produces 852 reproducible tasks, each paired with recovered fixtures, rewritten prompts, role classes, skill subclasses, hard rules, and semantic rubrics. Because the sessions contain internal enterprise content, we do not release the benchmark data; instead, our reusable contribution is the construction and evaluation protocol. On EnterpriseClawBench, the best configuration reaches only 0.663 (Codex with GPT-5.5). These results show that enterprise agent evaluation must report harness--model combinations, artifact delivery, visual quality, cost, runtime, and skill-transfer behavior, rather than collapsing performance into a single score. Code: https://github.com/FrontisAI/EnterpriseClawBench

Coding-agent benchmarks evaluate whether a single uninterrupted agent can resolve a repository issue. Real software work is messier: tasks are interrupted, reassigned, reviewed, and resumed from partial states left by another agent or engineer. We study this missing dimension through handoff debt: the rediscovery cost imposed when a predecessor's work is opaque or incomplete. Our takeover protocol interrupts a coding agent at deterministic handoff points, freezes the repository, and evaluates successor agents under four handoff views: repository state only, raw trace, summary notes, and structured notes. Across 75 source tasks, the protocol generates 181 handoff-point tasks and 724 takeover runs per successor model. Across three successor models, context-bearing handoffs reduce median agent events by 20-59% and cumulative prompt tokens by 42-63% relative to repository-only takeover. Solved-rate effects are smaller and model-dependent, but efficiency gains are consistent. These findings suggest that coding-agent evaluation should report not only whether a task is solved, but also how costly that work is for another agent to resume.

Geospatial foundation models (GFMs) have been proposed as generalizable backbones for disaster response, land-cover mapping, food-security monitoring, and other high-stakes Earth-observation tasks. Yet the published work about these models does not give reviewers or users enough information to tell which model fits a given task. We argue that nobody knows what the current state of the art is in geospatial foundation models. The methods may be useful, but the GFM literature does not standardize evaluations, training and testing protocols, released weights, or pretraining controls well enough for anyone to compare or rank them. In a 152-paper audit, we find 46 cross-paper disagreements of at least 10 points for the same model, benchmark, and protocol; 94/126 papers with extractable pretraining data use a configuration no other paper uses; and 39% of GFM papers release no model weights. This lack of community standards can be solved. We propose six concrete expectations: named-license weight release, shared core evaluations, copied-versus-rerun baseline annotations, variance reporting, one shared evaluation harness, and data-vs-architecture-vs-algorithm controls. These gaps are a coordination failure, not a fault of any individual lab; the authors of this paper, like many others in the GFM community, have contributed to them. Rather than just critiquing the community, we aim to provide concrete steps toward a shared understanding of how to innovate GFMs.

Event understanding aims at understanding the content and relationship of events within texts, which covers multiple complicated information extraction tasks: event detection, event argument extraction, and event relation extraction. To facilitate related research and application, we present an event understanding toolkit OmniEvent, which features three desiderata: (1) Comprehensive. OmniEvent supports mainstream modeling paradigms of all the event understanding tasks and the processing of 15 widely-used English and Chinese datasets. (2) Fair. OmniEvent carefully handles the inconspicuous evaluation pitfalls reported in Peng et al. (2023), which ensures fair comparisons between different models. (3) Easy-to-use. OmniEvent is designed to be easily used by users with varying needs. We provide off-the-shelf models that can be directly deployed as web services. The modular framework also enables users to easily implement and evaluate new event understanding models with OmniEvent. The toolkit (https://github.com/THU-KEG/OmniEvent) is publicly released along with the demonstration website and video (https://omnievent.xlore.cn/).

Agentic LLM coding tools compress long session histories into compaction summaries that subsequent sessions inherit as ground truth. This paper documents a failure mode in Claude Code where partial standard output from timed-out commands (exit code 143) is recorded in compaction summaries as confirmed results, propagating false positives across sessions and model versions without re-verification. The underlying mechanism is a conflation of observation and persistence, where information that appeared in the terminal is treated as equivalent to information written to durable storage. This finding extends the analysis of LLM self-evaluation failures reported in prior work on non-determinism in LLM-as-judge grading by showing that agentic tools exhibit analogous reliability deficits when reporting on their own operational outcomes. The failure has direct implications for any workflow that relies on agentic session continuity for data processing, scientific computation, or multi-step automation.

With the rapid advancement of Deep Research Agents in knowledge-intensive domains such as finance, establishing reliable and domain-aligned evaluation standards remains a critical challenge. Existing benchmarks focus on either closed-ended question answering or open-ended report evaluation, failing to jointly capture retrieval-reasoning accuracy and end-to-end research quality required in real-world workflows. We introduce ICBCBench, a consortium-driven benchmark for financial deep research, developed in collaboration with domain experts from a broad range of financial institutions and academia, involving over 50 experts across more than 40 organizations. It adopts a dual-track paradigm integrating objective tasks with verifiable answers and subjective long-form report evaluation, enabling complementary assessment of retrieval-reasoning accuracy and end-to-end report quality in terms of expert alignment, citation consistency, and source quality. Experiments on state-of-the-art DRAs and large language models reveal substantial gaps in complex reasoning, factual grounding, and report quality, highlighting the challenges of achieving industry-level performance. Our dataset and evaluation framework are available at https://github.com/DeepFin-Intelligence/ICBCBench.

Radiology reports convey detailed clinical observations and capture diagnostic reasoning that evolves over time. However, existing evaluation methods are limited to single-report settings and rely on coarse metrics that fail to capture fine-grained clinical semantics and temporal dependencies. We introduce LUNGUAGE,a benchmark dataset for structured radiology report generation that supports both single-report evaluation and longitudinal patient-level assessment across multiple studies. It contains 1,473 annotated chest X-ray reports, each reviewed by experts, and 80 of them contain longitudinal annotations to capture disease progression and inter-study intervals, also reviewed by experts. Using this benchmark, we develop a two-stage framework that transforms generated reports into fine-grained, schema-aligned structured representations, enabling longitudinal interpretation. We also propose LUNGUAGESCORE, an interpretable metric that compares structured outputs at the entity, relation, and attribute level while modeling temporal consistency across patient timelines. These contributions establish the first benchmark dataset, structuring framework, and evaluation metric for sequential radiology reporting, with empirical results demonstrating that LUNGUAGESCORE effectively supports structured report evaluation. The code is available at: https://github.com/SuperSupermoon/Lunguage

The quality of automatic metrics for machine translation has been increasingly called into question, especially for high-quality systems. This paper demonstrates that, while choice of metric is important, the nature of the references is also critical. We study different methods to collect references and compare their value in automated evaluation by reporting correlation with human evaluation for a variety of systems and metrics. Motivated by the finding that typical references exhibit poor diversity, concentrating around translationese language, we develop a paraphrasing task for linguists to perform on existing reference translations, which counteracts this bias. Our method yields higher correlation with human judgment not only for the submissions of WMT 2019 English to German, but also for Back-translation and APE augmented MT output, which have been shown to have low correlation with automatic metrics using standard references. We demonstrate that our methodology improves correlation with all modern evaluation metrics we look at, including embedding-based methods. To complete this picture, we reveal that multi-reference BLEU does not improve the correlation for high quality output, and present an alternative multi-reference formulation that is more effective.

Surgical phase recognition is a basic component for different context-aware applications in computer- and robot-assisted surgery. In recent years, several methods for automatic surgical phase recognition have been proposed, showing promising results. However, a meaningful comparison of these methods is difficult due to differences in the evaluation process and incomplete reporting of evaluation details. In particular, the details of metric computation can vary widely between different studies. To raise awareness of potential inconsistencies, this paper summarizes common deviations in the evaluation of phase recognition algorithms on the Cholec80 benchmark. In addition, a structured overview of previously reported evaluation results on Cholec80 is provided, taking known differences in evaluation protocols into account. Greater attention to evaluation details could help achieve more consistent and comparable results on the surgical phase recognition task, leading to more reliable conclusions about advancements in the field and, finally, translation into clinical practice.

With the advent of new sequence models like Mamba and xLSTM, several studies have shown that these models match or outperform state-of-the-art models in single-channel speech enhancement, automatic speech recognition, and self-supervised audio representation learning. However, prior research has demonstrated that sequence models like LSTM and Mamba tend to overfit to the training set. To address this issue, previous works have shown that adding self-attention to LSTMs substantially improves generalization performance for single-channel speech enhancement. Nevertheless, neither the concept of hybrid Mamba and time-frequency attention models nor their generalization performance have been explored for speech enhancement. In this paper, we propose a novel hybrid architecture, MambAttention, which combines Mamba and shared time- and frequency-multi-head attention modules for generalizable single-channel speech enhancement. To train our model, we introduce VoiceBank+Demand Extended (VB-DemandEx), a dataset inspired by VoiceBank+Demand but with more challenging noise types and lower signal-to-noise ratios. Trained on VB-DemandEx, our proposed MambAttention model significantly outperforms existing state-of-the-art LSTM-, xLSTM-, Mamba-, and Conformer-based systems of similar complexity across all reported metrics on two out-of-domain datasets: DNS 2020 and EARS-WHAM_v2, while matching their performance on the in-domain dataset VB-DemandEx. Ablation studies highlight the role of weight sharing between the time- and frequency-multi-head attention modules for generalization performance. Finally, we explore integrating the shared time- and frequency-multi-head attention modules with LSTM and xLSTM, which yields a notable performance improvement on the out-of-domain datasets. However, our MambAttention model remains superior on both out-of-domain datasets across all reported evaluation metrics.

Texture recognition remains challenging for modern vision models because discriminative evidence is often carried by higher-order spatial statistics rather than by object shape alone. While Vision Transformers provide strong long-range modeling capacity, their standard object-centric representations do not explicitly expose such statistical structure, which limits texture sensitivity in fine-grained recognition settings. We present HiPerViT, a compact vision-only architecture that injects an explicit second-order statistical prior into a transformer-based recognition pipeline. The method combines global and local image views with a compact bilinear descriptor encoded as a statistical token, and integrates this token with first-order spatial representations through Perceiver-style latent distillation. This design enables direct interaction between spatial tokens and second-order feature co-occurrence statistics, providing the model with explicit access to texture-relevant information without requiring multimodal pretraining or ensemble construction. Across six texture recognition benchmarks, HiPerViT achieves consistent improvements over strong vision-only baselines under the reported evaluation protocols, including gains of +3.05 percentage points on DTD, +10.48 on GTOS-Mobile, and +10.10 on 1200Tex. Beyond benchmark performance, our analyses show that these gains are largely invariant to the backbone depth used to extract second-order statistics and to the ordering of interaction and distillation stages. This pattern suggests that the primary source of improvement is not a specific fusion topology, but the explicit availability of second-order statistical information as a first-class representational signal. These results support explicit statistical tokenization as an effective and robust design principle for texture-centric visual recognition.

The proliferation of disinformation demands reliable and scalable fact-checking solutions. We present Dynamic Evidence-based FAct-checking with Multimodal Experts (DEFAME), a modular, zero-shot MLLM pipeline for open-domain, text-image claim verification. DEFAME operates in a six-stage process, dynamically selecting the tools and search depth to extract and evaluate textual and visual evidence. Unlike prior approaches that are text-only, lack explainability, or rely solely on parametric knowledge, DEFAME performs end-to-end verification, accounting for images in claims and evidence while generating structured, multimodal reports. Evaluation on the popular benchmarks VERITE, AVerITeC, and MOCHEG shows that DEFAME surpasses all previous methods, establishing itself as the new state-of-the-art fact-checking system for uni- and multimodal fact-checking. Moreover, we introduce a new multimodal benchmark, ClaimReview2024+, featuring claims after the knowledge cutoff of GPT-4o, avoiding data leakage. Here, DEFAME drastically outperforms the GPT-4o baselines, showing temporal generalizability and the potential for real-time fact-checking.

Repository-level code review requires reasoning over project structure, repository context, and file-level implementation details. Existing automated review workflows often collapse these tasks into a single pass, which can reduce relevance, increase duplication, and weaken prioritization. We present RepoReviewer, a local-first multi-agent system for automated GitHub repository review with a Python CLI, FastAPI API, LangGraph orchestration layer, and Next.js user interface. RepoReviewer decomposes review into repository acquisition, context synthesis, file-level analysis, finding prioritization, and summary generation. We describe the system design, implementation tradeoffs, developer-facing interfaces, and practical failure modes. Rather than claiming benchmark superiority, we frame RepoReviewer as a technical systems contribution: a pragmatic architecture for repository-level automated review, accompanied by reusable evaluation and reporting infrastructure for future empirical study.

The evaluation of generated reports remains a critical challenge in Computed Tomography (CT) report generation, due to the large volume of text, the diversity and complexity of findings, and the presence of fine-grained, disease-oriented attributes. Conventional evaluation metrics offer only coarse measures of lexical overlap or entity matching and fail to reflect the granular diagnostic accuracy required for clinical use. To address this gap, we propose CT-FineBench, a benchmark built from CT-RATE and Merlin to evaluate the fine-grained factual consistency of CT reports, constructed from CT-RATE and Merlin. Our benchmark is constructed through a meticulous, Question-Answering (QA) based process: first, we identify and structure key, finding-specific clinical attributes (like location, size, margin). Second, we systematically transform these attributes into a QA dataset, where questions probe for specific clinical details grounded in gold-standard reports. The evaluation protocol for CT-FineBench involves using this QA dataset to query a machine-generated report and scoring the correctness of the answers. This allows for a comprehensive, interpretable, and clinically-relevant assessment, moving beyond superficial lexical overlap to pinpoint specific clinical errors. Experiments show that CT-FineBench correlates better with expert clinical assessment and is substantially more sensitive to fine-grained factual errors than prior metrics.

Generation of long-form, citation-backed reports is a primary use case for retrieval augmented generation (RAG) systems. While open-source evaluation tools exist for various RAG tasks, ones tailored to report generation (RG) are lacking. Accordingly, we introduce Auto-ARGUE, a robust LLM-based implementation of the recently proposed ARGUE framework for RG evaluation. We present analysis of Auto-ARGUE on the RG pilot task from the TREC 2024 NeuCLIR track, showing good system-level correlations with human judgments. We further release a web app for visualization of Auto-ARGUE outputs.

As an embodiment of intelligence evolution toward interconnected architectures, Deep Research Agents (DRAs) systematically exhibit the capabilities in task decomposition, cross-source retrieval, multi-stage reasoning, information integration, and structured output, which markedly enhance performance on complex and open-ended tasks. However, existing benchmarks remain deficient in evaluation dimensions, response format, and scoring mechanisms, limiting their effectiveness in assessing such agents. This paper introduces Dr. Bench, a multidimensional evaluation framework tailored to DRAs and long-form report-style responses. The benchmark comprises 214 expert-curated challenging tasks across 10 broad domains, each accompanied by manually constructed reference bundles to support composite evaluation. This framework incorporates metrics for semantic quality, topical focus, and retrieval trustworthiness, enabling a comprehensive evaluation of long reports generated by DRAs. Extensive experimentation confirms the superior performance of mainstream DRAs over web-search-tool-augmented reasoning models, yet reveals considerable scope for further improvement. This study provides a robust foundation for capability assessment, architectural refinement, and paradigm advancement of DRAs.

Radiology reporting is a complex task that requires detailed image understanding, integration of multiple inputs, including comparison with prior imaging, and precise language generation. This makes it ideal for the development and use of generative multimodal models. Here, we extend report generation to include the localisation of individual findings on the image - a task we call grounded report generation. Prior work indicates that grounding is important for clarifying image understanding and interpreting AI-generated text. Therefore, grounded reporting stands to improve the utility and transparency of automated report drafting. To enable evaluation of grounded reporting, we propose a novel evaluation framework - RadFact - leveraging the reasoning capabilities of large language models (LLMs). RadFact assesses the factuality of individual generated sentences, as well as correctness of generated spatial localisations when present. We introduce MAIRA-2, a large multimodal model combining a radiology-specific image encoder with a LLM, and trained for the new task of grounded report generation on chest X-rays. MAIRA-2 uses more comprehensive inputs than explored previously: the current frontal image, the current lateral image, the prior frontal image and prior report, as well as the Indication, Technique and Comparison sections of the current report. We demonstrate that these additions significantly improve report quality and reduce hallucinations, establishing a new state of the art on findings generation (without grounding) on MIMIC-CXR while demonstrating the feasibility of grounded reporting as a novel and richer task.

Both capability and safety benchmarks rest upon the assumption that the behavior of language models undergoing a test is informative about their behavior in deployment. This assumption can fail, should models infer that they are being evaluated and condition their response on such context. This hypothesis, termed ``evaluation awareness'', has been observed in frontier and open-weight language models alike. We provide a systematic study of this phenomenon, by probing for it across six language models (from four families and three sizes) and three metrics. More precisely, we examine whether (i) being under evaluation is linearly represented within the models' activations space, (ii) it is verbalized in their output tokens (as scored by an LLM-as-judge), and (iii) steering causally affects their behavior. For the open-checkpoint Olmo models, we further test these measures at every training stage. In doing so, we report that evaluation awareness is linearly decodable from the residual streams of every model (best AUROC geq 0.7). By contrast, these representations align only in part with verbalization: their correlations and mutual information are nonzero in some settings, yet vary substantially across models, layers, and readout choices. Nevertheless, steering along probe-derived directions can shift the verbalization scores. Finally, a comparison across the Olmo checkpoints reveals that evaluation awareness is already present within base models, becomes amplified throughout the stages of supervised fine-tuning, and remains stable thereafter---unlike the effects of steering, that grow more pronounced at every successive training stage. These results show the need for evaluations to account for the disjunction between what models represent internally, what they verbalize, and their steering.

Breast cancer is a major global health concern, and mammography screening plays a central role in early detection. The large volume of screening examinations creates a substantial workload for radiologists, making accurate and consistent report generation a critical clinical challenge. Existing automated mammography report generation methods primarily focus on direct visual-to-text mapping, while overlooking the structured clinical reasoning process followed by radiologists in real-world practice. To address this limitation, we propose MammoRG, a mammography report generation framework that explicitly simulates the clinical reporting workflow by following the BI-RADS guideline and incorporating prior clinical knowledge to produce diagnostic reports. Specifically, MammoRG adopts a two-stage training framework. In the first stage, the model learns to integrate clinically relevant prior knowledge from a patient's four-view mammograms through classification-based supervision. In the second stage, a terminology-aware supervised fine-tuning strategy is introduced to model mammography-specific clinical terms as atomic semantic units, enabling the generation of high-quality reports with improved clinical consistency. To facilitate clinical efficacy evaluation of generated reports, we further develop MammoRGTool, a dedicated mammography report parsing tool that extracts structured clinical information from free-text reports. Extensive experiments demonstrate that MammoRG consistently outperforms existing methods across multiple clinical efficacy metrics, particularly in diagnosis-related BI-RADS F1, where it surpasses the second-best model by 2.73%, 2.04%, 1.90%, and 3.27% on the internal, external 1, external 2, and VinDr-Mammo datasets, respectively.

VLM safety is commonly evaluated through input- and output-level classification. Such classification is necessary, but it does not reveal whether a safety state is accessible or controllable inside the model. We argue that multimodal safety evaluation should therefore report a controllability profile alongside behavioral classification, separating representation-level detectability, cross-modal specificity, intervention sensitivity, and benign-preserving selectivity. Using implicit toxicity as a stress case, we instantiate this profile on LlavaGuard and Qwen3.5 with sparse feature decompositions. LlavaGuard admits localized handles with a narrow benign-preserving intervention range and modest downstream safety gains, whereas Qwen3.5 supports strong representation-level readout but no comparable selective-control regime under the tested operators. These results show that internal readout and controllability can diverge. Future multimodal safety benchmarks should therefore report not only behavioral safety metrics, but also whether safety-relevant internal signals can be intervention-tested and controlled within a validated operating range.

Frontier models have demonstrated remarkable capabilities in understanding and reasoning with natural-language text, but they still exhibit major competency gaps in multimodal understanding and reasoning especially in high-value verticals such as biomedicine. Medical imaging report generation is a prominent example. Supervised fine-tuning can substantially improve performance, but they are prone to overfitting to superficial boilerplate patterns. In this paper, we introduce Universal Report Generation (UniRG) as a general framework for medical imaging report generation. By leveraging reinforcement learning as a unifying mechanism to directly optimize for evaluation metrics designed for end applications, UniRG can significantly improve upon supervised fine-tuning and attain durable generalization across diverse institutions and clinical practices. We trained UniRG-CXR on publicly available chest X-ray (CXR) data and conducted a thorough evaluation in CXR report generation with rigorous evaluation scenarios. On the authoritative ReXrank benchmark, UniRG-CXR sets new overall SOTA, outperforming prior state of the art by a wide margin.

This paper introduces a novel, entity-aware metric, termed as Radiological Report (Text) Evaluation (RaTEScore), to assess the quality of medical reports generated by AI models. RaTEScore emphasizes crucial medical entities such as diagnostic outcomes and anatomical details, and is robust against complex medical synonyms and sensitive to negation expressions. Technically, we developed a comprehensive medical NER dataset, RaTE-NER, and trained an NER model specifically for this purpose. This model enables the decomposition of complex radiological reports into constituent medical entities. The metric itself is derived by comparing the similarity of entity embeddings, obtained from a language model, based on their types and relevance to clinical significance. Our evaluations demonstrate that RaTEScore aligns more closely with human preference than existing metrics, validated both on established public benchmarks and our newly proposed RaTE-Eval benchmark.

AI-driven models have demonstrated significant potential in automating radiology report generation for chest X-rays. However, there is no standardized benchmark for objectively evaluating their performance. To address this, we present ReXrank, https://rexrank.ai, a public leaderboard and challenge for assessing AI-powered radiology report generation. Our framework incorporates ReXGradient, the largest test dataset consisting of 10,000 studies, and three public datasets (MIMIC-CXR, IU-Xray, CheXpert Plus) for report generation assessment. ReXrank employs 8 evaluation metrics and separately assesses models capable of generating only findings sections and those providing both findings and impressions sections. By providing this standardized evaluation framework, ReXrank enables meaningful comparisons of model performance and offers crucial insights into their robustness across diverse clinical settings. Beyond its current focus on chest X-rays, ReXrank's framework sets the stage for comprehensive evaluation of automated reporting across the full spectrum of medical imaging.

Automated radiology report generation from chest X-ray (CXR) images has the potential to improve clinical efficiency and reduce radiologists' workload. However, most datasets, including the publicly available MIMIC-CXR and CheXpert Plus, consist entirely of free-form reports, which are inherently variable and unstructured. This variability poses challenges for both generation and evaluation: existing models struggle to produce consistent, clinically meaningful reports, and standard evaluation metrics fail to capture the nuances of radiological interpretation. To address this, we introduce Structured Radiology Report Generation (SRRG), a new task that reformulates free-text radiology reports into a standardized format, ensuring clarity, consistency, and structured clinical reporting. We create a novel dataset by restructuring reports using large language models (LLMs) following strict structured reporting desiderata. Additionally, we introduce SRR-BERT, a fine-grained disease classification model trained on 55 labels, enabling more precise and clinically informed evaluation of structured reports. To assess report quality, we propose F1-SRR-BERT, a metric that leverages SRR-BERT's hierarchical disease taxonomy to bridge the gap between free-text variability and structured clinical reporting. We validate our dataset through a reader study conducted by five board-certified radiologists and extensive benchmarking experiments.

We present Arkios, a 1.04B-parameter dense transformer pretrained from scratch on 150B tokens of bilingual English-Nepali text, using a custom single-file C/CUDA training stack and a Devanagari-aware byte-level BPE tokenizer built for this project. On ARC-Easy and ARC-Challenge, Arkios exceeds three comparably sized open models (Pythia-1.4B, TinyLlama-1.1B, OLMo-1B) despite an order of magnitude fewer training tokens, likely aided by a match between our educational-web-text pretraining data and ARC's grade-school-science format rather than a general capability advantage. We report full evaluation results under standard protocols, including a correction to an earlier partial-sample estimate, and findings specific to evaluating small models in a low-resource language: the standard multiple-choice-letter prompt format used by common evaluation harnesses places this model at chance on Nepali reading comprehension, and simultaneously at chance on English in the same format, which would lead a naive benchmark run to conclude the model has no Nepali ability when in fact it does. Concretely, both languages score at chance in the letter-choice format (0.240 Nepali, 0.236 English, against a chance baseline of 0.250), while scoring the answer text directly reveals genuine, English-favoring comprehension (0.306 Nepali, 0.387 English). We describe a manifest-conditioned tool-use contract introduced during instruction tuning, where tool calls are permitted only when a tool manifest is declared in context and suppressed otherwise, and report where that contract holds and where it does not. We release both the base and instruction-tuned model weights under Apache-2.0. The training code and a small privately-sourced portion of the Nepali pretraining corpus are not released; everything needed to reproduce the reported numbers from the released weights is included here.

ARC-AGI-3 evaluates agents in interactive environments whose rules and objectives must be inferred from observation. We present Kepler, an open-source harness that represents hypotheses as executable world models and validates them through retrospective transition checks and conditional prediction checks. Under one frozen Claude Opus 5 configuration, Kepler obtained a server-verified 100.00 RHAE on all 25 public games, with no per-game model selection or score-conditioned reruns. On 181 of 183 completed levels, the final Opus attempt used no more actions than the corresponding median-human baseline. The retained board runs used 8,256 environment actions, of which 7,292 occurred in scored levels. Retained local provider-session records yield 858.0 million tokens, 97.37% cache reads, and a \$777.72 cost at September 1, 2026 API list-equivalent rates. We also report three evaluation failures: source-code leakage that produced an invalid perfect run, agents reconstructing a removed harness in a control condition, and autonomous repair masking a broken planner. A single-game observation case study showed that animation frames contained task-relevant information absent from settled text grids. Across the final Claude Opus 5 and GPT-5.6 Sol boards, 48 of 50 game-model cells reached 100. These results indicate that public-set score alone has limited discriminative value and motivate first-attempt, cost-conditioned, and verification-aware reporting.

AI evaluation suites often report many scores without checking whether those scores carry independent information. We introduce Effective Dimensionality (ED), the participation ratio of a centered benchmark-score spectrum, as a fast, population-conditional upper-bound diagnostic of measurement breadth. Applied at per-instance granularity to 22 benchmarks across 8 domains and more than 8,400 model evaluations, ED reveals substantial redundancy: the six-score Open LLM Leaderboard behaves like roughly two effective measurement axes (ED = 1.7), BBH and MMLU-Pro are near-interchangeable (rho = 0.96, stable across seven subpopulations), and measurement breadth varies more than 20x across current benchmarks. We show that relative ED rankings are stable under matched-dimension controls and that ED can flag redundant suite components, monitor performance-conditional compression, and guide benchmark maintenance. Because binary spectra overestimate absolute latent dimensionality, we interpret ED as a screening statistic rather than a literal factor count and complement it with null, reliability, and saturation analyses. We provide a 22-benchmark reference atlas and a four-step diagnostic workflow that benchmark maintainers can run with a score matrix and a few lines of code.

Camera trajectories control viewpoint changes in video generation, scene reconstruction, and robotic perception. Generating them from language requires both scene geometry and target-aware framing. We introduce OmniCam, an autoregressive model that generates camera pose sequences from a single panorama and textual trajectory descriptions. Its geometry-grounded pose token learning combines three components: a panoramic point-cloud encoder for omnidirectional geometric context; hybrid absolute-rotation and relative-translation tokenization with temporally consistent quaternion signs; and separate geometric and semantic conditioning streams with an explicit 3D target anchor. We also construct OmniCaT, containing 267,700 trajectories across four camera behaviors. On the reported OmniCaT evaluation, OmniCam reduces trajectory errors by 28--47% and collision rate by 65.8% relative to GenDoP retrained on OmniCaT. Against the best baseline for each metric, the ATE and collision reductions are 43.0% and 62.3%, respectively. Component ablations support the use of geometric and target-aware conditioning, while downstream experiments examine camera-controlled video generation and robotic active perception.

Although document OCR systems perform increasingly well on routine documents, complex formulas, structured text, and long-tail formats remain error-prone. OCR predictions may omit fine-grained content or hallucinate unsupported outputs, while equivalent encodings of the same visible content must be accommodated. Existing OCR evaluation methods mostly report aggregate metrics, offering limited support for analyzing case-level errors and improving OCR performance. We propose OCR-EDR (OCR Error Diagnosis and Repair), a rendering-aware framework that advances from fine-grained diagnosis to iterative repair. Given a source image, an editable OCR prediction, and its rendered image, OCR-EDR first jointly assesses whether the prediction and its rendering are consistent with the source, preserving valid predictions, including rendering-equivalent ones, while diagnosing and localizing genuine errors. It then applies executable edits and may request an updated rendering for iterative reassessment. We construct OCRErrBench from diverse real OCR predictions, covering text and formulas, exact and rendering-equivalent positives, and genuine errors, and develop the DocEDR model to execute the diagnosis--repair loop. On OCRErrBench, DocEDR achieves 94.78% diagnostic accuracy. It repairs 86.23% of erroneous inputs to visual consistency, raises formula Case-F1 by 30.99 percentage points over DOCR-Inspector-7B on DOCRcaseBench, and improves formula CDM by up to 4.62 percentage points on the identified Bad subsets of four OCR systems on UniMER-Test. These results show that OCR-EDR turns fine-grained OCR analysis into verified corrections and performance gains.

Multi-turn LLM evaluation is typically reported as a single win-rate scalar, conflating distinct capabilities. We introduce AIDG (Adversarial Information Deduction Game), formalizing multi-turn adversarial dialogue as a two-player partially observable stochastic game (POSG) and decomposing performance along Seeker (extraction) and Holder (containment) roles. The decomposition isolates three failure modes: cooperative-prior leakage, constraint-reasoning interference, and inefficient hypothesis-space traversal. Across 439 games over six frontier LLMs, defensive performance is tightly clustered (sigma = 1.9 ELO) while offensive performance varies substantially (sigma = 53.3 ELO); confirmation framing increases extraction odds 7.75x over uninformed deduction (p < 0.00001); and constraint violations account for 41.3% of deductive failures, uncorrelated with scale (rho = 0.0). We position the containment-over-extraction gap not as a surprising finding but as a measurable consequence of locally resolvable defensive decisions versus globally coupled offensive planning, and use the decomposition to attribute the gap per model. All design choices, including turn-decay weighting and the Bradley-Terry rating model, are derived from explicit assumptions.

LLM-as-judge ("grader") components are now standard in evaluation harnesses, including safety evaluations where a pass/fail verdict may gate downstream deployment decisions. A widespread assumption is that setting the grader's sampling temperature to 0 makes grading deterministic. We test this assumption against a real safety-evaluation codebase (Japan AISI's open-source aisev) and show it fails on two levels. First, the harness invokes its grader without setting temperature or seed; the underlying provider silently applies its default of 1.0, so items near the decision boundary flip pass/fail across identical runs (per-item disagreement up to ~50% over 20 runs). Second, pinning temperature=0 reduces but does not eliminate flips: across 690 API calls spanning two providers, three model tiers, and five sampling configurations, 1-2 of 7 borderline items remain non-reproducible even under forced greedy decoding (top_k=1). Claude Opus 4.7/4.8 has since deprecated temperature entirely, rendering the primary mitigation inapplicable to newer model generations. These findings expose a structural gap: evaluation harnesses that report single-run verdicts without variance or grader-disagreement metrics can present noise as a safety property. We release a reproduction harness (690 calls, 7 conditions) and recommend that harnesses treat grader disagreement as a first-class health metric alongside the scores themselves.

Large language models (LLMs) are increasingly deployed in settings where reasoning, such as multi-step problem solving and chain-of-thought, is essential. Yet, current evaluation practices overwhelmingly report single-run accuracy while ignoring the intrinsic uncertainty that naturally arises from stochastic decoding. This omission creates a blind spot because practitioners cannot reliably assess whether a method's reported performance is stable, reproducible, or cost-consistent. We introduce ReasonBENCH, the first benchmark designed to quantify the underlying instability in LLM reasoning. ReasonBENCH provides (i) a modular evaluation library that standardizes reasoning frameworks, models, and tasks, (ii) a multi-run protocol that reports statistically reliable metrics for both quality and cost, and (iii) a public leaderboard to encourage variance-aware reporting. Across tasks from different domains, we find that the vast majority of reasoning strategies and models exhibit high instability. Notably, even strategies with similar average performance can display confidence intervals up to four times wider, and the top-performing methods often incur higher and less stable costs. Such instability compromises reproducibility across runs and, consequently, the reliability of reported performance. To better understand these dynamics, we further analyze the impact of prompts, model families, and scale on the trade-off between solve rate and stability. Our results highlight reproducibility as a critical dimension for reliable LLM reasoning and provide a foundation for future reasoning methods and uncertainty quantification techniques. ReasonBENCH is publicly available at https://github.com/au-clan/ReasonBench .

As automated reasoning systems advance rapidly, there is a growing need for research-level formal mathematical problems to accurately evaluate their capabilities. To address this, we present Formal Conjectures, an evolving benchmark of currently 2615 mathematical problem statements formalized in Lean 4. Sourced from areas of active mathematical research, the dataset features 1029 open research conjectures providing a zero-contamination benchmark for mathematical proof discovery, and 836 solved problems for proof autoformalization. Notably, the repository provides a structured interface connecting mathematicians who formalize and clarify problems with the AI systems and humans attempting to solve them. Demonstrating its immediate utility, the benchmark has already been leveraged to make new mathematical discoveries, including the resolution of open research conjectures. We describe our approach to ensuring the correctness of these formalizations in a collaborative open-source project where contributions stem from an active community. In this framework, AI-generated proofs and disproofs serve as a valuable auditing mechanism to iteratively improve the fidelity of the benchmark. Finally, we provide a standardized evaluation setup and report baseline results on frozen evaluation subsets, demonstrating a climbable signal that measures the current frontier of automated reasoning on research-level mathematics.

Deep Research Agents (DRAs) generate citation-rich reports via multi-step search and synthesis, yet existing benchmarks mainly target text-only settings or short-form multimodal QA, missing end-to-end multimodal evidence use. We introduce MMDeepResearch-Bench (MMDR-Bench), a benchmark of 140 expert-crafted tasks across 21 domains, where each task provides an image-text bundle to evaluate multimodal understanding and citation-grounded report generation. Compared to prior setups, MMDR-Bench emphasizes report-style synthesis with explicit evidence use, where models must connect visual artifacts to sourced claims and maintain consistency across narrative, citations, and visual references. We further propose a unified, interpretable evaluation pipeline: Formula-LLM Adaptive Evaluation (FLAE) for report quality, Trustworthy Retrieval-Aligned Citation Evaluation (TRACE) for citation-grounded evidence alignment, and Multimodal Support-Aligned Integrity Check (MOSAIC) for text-visual integrity, each producing fine-grained signals that support error diagnosis beyond a single overall score. Experiments across 25 state-of-the-art models reveal systematic trade-offs between generation quality, citation discipline, and multimodal grounding, highlighting that strong prose alone does not guarantee faithful evidence use and that multimodal integrity remains a key bottleneck for deep research agents.

Automatic speech recognition systems have undoubtedly advanced with the integration of multilingual and multitask models such as Whisper, which have shown a promising ability to understand and process speech across a wide range of languages. Despite their robustness, these models often fall short in handling the linguistic distinctions of minority languages. This study addresses this gap by integrating traditional and novel language models with fine-tuned Whisper models to raise their performance in less commonly studied languages. Through rigorous fine-tuning and evaluation across multiple datasets, we demonstrate substantial improvements in word error rate, particularly in low-resource scenarios. Our approach not only does take advantage of the extensive data Whisper was pre-trained on, but also complements its linguistic adaptability by incorporating language models. We obtained improvements up to 51\% for in-distribution datasets and up to 34\% for out-of-distribution sentences using statistical language models, while large language models provided moderate but consistently robust improvement across diverse linguistic contexts. The findings reveal that, while the integration reliably benefits all model sizes, the extent of improvement varies, highlighting the importance of optimized language model parameters. Finally, we emphasize the importance of selecting appropriate evaluation parameters when reporting the results using transformer-based ASR models. In summary, this research clears the way for more inclusive ASR technologies that perform better across languages by enriching their linguistic knowledge. For further implementation details of this study, the technical documentation and source code are available at http://www.github.com/hitz-zentroa/whisper-lm.

We are witnessing a modeling shift from CNN to Transformers in computer vision. In this work, we present a self-supervised learning approach called MoBY, with Vision Transformers as its backbone architecture. The approach basically has no new inventions, which is combined from MoCo v2 and BYOL and tuned to achieve reasonably high accuracy on ImageNet-1K linear evaluation: 72.8% and 75.0% top-1 accuracy using DeiT-S and Swin-T, respectively, by 300-epoch training. The performance is slightly better than recent works of MoCo v3 and DINO which adopt DeiT as the backbone, but with much lighter tricks. More importantly, the general-purpose Swin Transformer backbone enables us to also evaluate the learnt representations on downstream tasks such as object detection and semantic segmentation, in contrast to a few recent approaches built on ViT/DeiT which only report linear evaluation results on ImageNet-1K due to ViT/DeiT not tamed for these dense prediction tasks. We hope our results can facilitate more comprehensive evaluation of self-supervised learning methods designed for Transformer architectures. Our code and models are available at https://github.com/SwinTransformer/Transformer-SSL, which will be continually enriched.

In order to improve reproducibility, deep reinforcement learning (RL) has been adopting better scientific practices such as standardized evaluation metrics and reporting. However, the process of hyperparameter optimization still varies widely across papers, which makes it challenging to compare RL algorithms fairly. In this paper, we show that hyperparameter choices in RL can significantly affect the agent's final performance and sample efficiency, and that the hyperparameter landscape can strongly depend on the tuning seed which may lead to overfitting. We therefore propose adopting established best practices from AutoML, such as the separation of tuning and testing seeds, as well as principled hyperparameter optimization (HPO) across a broad search space. We support this by comparing multiple state-of-the-art HPO tools on a range of RL algorithms and environments to their hand-tuned counterparts, demonstrating that HPO approaches often have higher performance and lower compute overhead. As a result of our findings, we recommend a set of best practices for the RL community, which should result in stronger empirical results with fewer computational costs, better reproducibility, and thus faster progress. In order to encourage the adoption of these practices, we provide plug-and-play implementations of the tuning algorithms used in this paper at https://github.com/facebookresearch/how-to-autorl.

The growing popularity and capacity of generative models have eroded the distinction between human and machine-generated content, motivating a growing body of work on detection across text, images, and audio. Most available detectors are either commercial software or, if open-source, come with incompatible codebases with bespoke preprocessing, evaluation protocols, and evaluation metrics, which make their adoption, fair comparison, and reproduction quite difficult. To address this critical gap, we introduce DetectZoo, a first-of-its-kind, extensible toolkit designed to provide a unified interface for AI-generated content detection across text, audio, and image modalities. DetectZoo standardizes the complete empirical pipeline, from data ingestion and preprocessing to model assessment, offering researchers a cohesive framework to benchmark state-of-the-art detectors systematically. By integrating diverse public datasets and baseline detection algorithms under a single, unified API, our toolkit facilitates rigorous and reproducible evaluation. DetectZoo provides reference implementations of 61 detectors, native loaders for 22 benchmark datasets, and a standardized evaluation pipeline that reports multiple metrics through a common interface. Each detector is self-contained yet accessible through the same interface, automatically caches pretrained weights, and reproduces the original published results. DetectZoo lowers the barrier to entry for multi-modal AI forensics, enabling researchers to identify performance gaps across domains and accelerating the development of robust, generalizable detection techniques. The open-source repository and comprehensive documentation are publicly available at https://github.com/sadjadeb/DetectZoo, and the package can be installed via pip install detectzoo.

Reporting quality is an important topic in clinical trial research articles, as it can impact clinical decisions. In this article, we test the ability of large language models to assess the reporting quality of this type of article using the Consolidated Standards of Reporting Trials (CONSORT). We create CONSORT-QA, an evaluation corpus from two studies on abstract reporting quality with CONSORT-abstract standards. We then evaluate the ability of different large generative language models (from the general domain or adapted to the biomedical domain) to correctly assess CONSORT criteria with different known prompting methods, including Chain-of-thought. Our best combination of model and prompting method achieves 85% accuracy. Using Chain-of-thought adds valuable information on the model's reasoning for completing the task.

The rapid development and dynamic nature of large language models (LLMs) make it difficult for conventional quantitative benchmarks to accurately assess their capabilities. We propose report cards, which are human-interpretable, natural language summaries of model behavior for specific skills or topics. We develop a framework to evaluate report cards based on three criteria: specificity (ability to distinguish between models), faithfulness (accurate representation of model capabilities), and interpretability (clarity and relevance to humans). We also propose an iterative algorithm for generating report cards without human supervision and explore its efficacy by ablating various design choices. Through experimentation with popular LLMs, we demonstrate that report cards provide insights beyond traditional benchmarks and can help address the need for a more interpretable and holistic evaluation of LLMs.

We conduct a moderate-scale contamination-free (to some extent) evaluation of current large reasoning models (LRMs) with some preliminary findings. We also release ROME, our evaluation benchmark for vision language models intended to test reasoning from visual clues. We attach links to the benchmark, evaluation data, and other updates on this website: https://flageval-baai.github.io/LRM-Eval/

Anticipating LLM behavioral tendencies from low-cost psychometric probes is critical for safe deployment, but only if self-reports (SR) reliably predict behavior. Recent work documented substantial SR-behavior dissociation in LLMs, but relied on broad personality traits (Big 5) that predict specific behaviors weakly, even in humans. Furthermore, the isolation of conversational sessions combined with weak context matching left open whether LLMs truly lack coherence or whether the conditions needed to detect such coherence were not met. We contrast Big 5 with the Theory of Planned Behavior (TPB), which measures intention targeted to a specific behavior and predicts human behavior substantially better than broad traits. We run experiments across four behavioral tasks and 11 frontier LLMs, while also varying session context and identity induction. We find that SR-behavior coherence exists but is selective. 1) Within a shared conversation, the Theory of Planned Behavior reaches human-level coherence; Big 5 does not. 2) Across separate conversations, coherence survives only for behaviors anchored outside the immediate prompt, such as implicit bias shaped by training, and collapses when behavior is strongly primed by context, as with sycophancy. 3) Persona prompting makes self-reports more consistent across conversations, but does not bring behavior into alignment. These findings suggest that coarse personality frameworks, such as Big 5 may not be the best tools for testing deployment behavior. More task- and behavior-specific instruments are needed, and even these must be evaluated across tasks and contexts.

Using large language models (LLMs) to assist psychological counseling is a significant but challenging task at present. Attempts have been made on improving empathetic conversations or acting as effective assistants in the treatment with LLMs. However, the existing datasets lack consulting knowledge, resulting in LLMs lacking professional consulting competence. Moreover, how to automatically evaluate multi-turn dialogues within the counseling process remains an understudied area. To bridge the gap, we propose CPsyCoun, a report-based multi-turn dialogue reconstruction and evaluation framework for Chinese psychological counseling. To fully exploit psychological counseling reports, a two-phase approach is devised to construct high-quality dialogues while a comprehensive evaluation benchmark is developed for the effective automatic evaluation of multi-turn psychological consultations. Competitive experimental results demonstrate the effectiveness of our proposed framework in psychological counseling. We open-source the datasets and model for future research at https://github.com/CAS-SIAT-XinHai/CPsyCoun

This is a report on the NSF Future Directions Workshop on Automatic Evaluation of Dialog. The workshop explored the current state of the art along with its limitations and suggested promising directions for future work in this important and very rapidly changing area of research.

This paper explores the potential of large language models (LLMs) to generate financial reports from time series data. We propose a framework encompassing prompt engineering, model selection, and evaluation. We introduce an automated highlighting system to categorize information within the generated reports, differentiating between insights derived directly from time series data, stemming from financial reasoning, and those reliant on external knowledge. This approach aids in evaluating the factual grounding and reasoning capabilities of the models. Our experiments, utilizing both data from the real stock market indices and synthetic time series, demonstrate the capability of LLMs to produce coherent and informative financial reports.

Automated radiology report generation for multi-sequence brain MRI holds strong promise for alleviating radiologists' workload, yet it remains a demanding problem: brain MRI studies are inherently volumetric, each pulse sequence carries complementary diagnostic information, and annotated data are critically scarce for low-resource clinical languages. Existing brain MRI-report resources are still dominated by English reports, translated clinical text, or datasets adapted from task-specific imaging benchmarks, leaving routine low-resource clinical reporting and heterogeneous multi-sequence MRI protocols insufficiently represented. To bridge this gap, we introduce ViBMR, to the best of our knowledge, the first large-scale multi-sequence brain MRI dataset paired with routine Vietnamese clinical reports, comprising 3,649 patients and 11,875 MRI series across T1, T2, FLAIR, and contrast-enhanced T1 sequences. Building on ViBMR, we establish a comprehensive evaluation setup for brain MRI report generation, covering representative medical vision-language models, multi-sequence inputs, and feature aggregation strategies. The results provide key insights into dataset characteristics and model behavior, while demonstrating the necessity of native low-resource clinical datasets for reliable Vietnamese-origin brain MRI report generation. Our dataset and baseline models will be released for non-commercial research.

Large language models (LLMs) now perform strongly on many public math suites, yet frontier separation within mathematics increasingly suffers from ceiling effects. We present two complementary benchmarks: SKYLENAGE-ReasoningMATH, a 100-item, structure-aware diagnostic set with per-item metadata on length, numeric density, and symbolic complexity; and SKYLENAGE-MATH, a 150-item contest-style suite spanning four stages from high school to doctoral under a seven-subject taxonomy. We evaluate fifteen contemporary LLM variants under a single setup and analyze subject x model and grade x model performance. On the contest suite, the strongest model reaches 44% while the runner-up reaches 37%; accuracy declines from high school to doctoral, and top systems exhibit a doctoral-to-high-school retention near 79%. On the reasoning set, the best model attains 81% overall, and hardest-slice results reveal clear robustness gaps between leaders and the mid-tier. In summary, we release SKYLENAGE-ReasoningMATH and report aggregate results for SKYLENAGE-MATH; together, SKYLENAGE provides a hard, reasoning-centered and broadly covering math benchmark with calibrated difficulty and rich metadata, serving as a reference benchmark for future evaluations of mathematical reasoning.

In the digital era, accidental exposure of sensitive information such as API keys, tokens, and credentials is a growing security threat. While most prior work focuses on detecting secrets in source code, leakage in software issue reports remains largely unexplored. This study fills that gap through a large-scale analysis and a practical detection pipeline for exposed secrets in GitHub issues. Our pipeline combines regular expression-based extraction with large language model (LLM)-based contextual classification to detect real secrets and reduce false positives. We build a benchmark of 54,148 instances from public GitHub issues, including 5,881 manually verified true secrets. Using this dataset, we evaluate entropy-based baselines and keyword heuristics used by prior secret detection tools, classical machine learning, deep learning, and LLM-based methods. Regex and entropy based approaches achieve high recall but poor precision, while smaller models such as RoBERTa and CodeBERT greatly improve performance (F1 = 92.70%). Proprietary models like GPT-4o perform moderately in few-shot settings (F1 = 80.13%), and fine-tuned open-source larger LLMs such as Qwen and LLaMA reach up to 94.49% F1. Finally, we also validate our approach on 178 real-world GitHub repositories, achieving an F1-score of 81.6% which demonstrates our approach's strong ability to generalize to in-the-wild scenarios.

Introduction. Generative Artificial Intelligence, particularly large language models (LLMs), offers transformative potential for Health Economics and Outcomes Research (HEOR). However, evaluating the quality, transparency, and rigor of LLM-assisted research lacks standardized guidance. This article introduces the ELEVATE AI LLMs framework and checklist, designed to support researchers and reviewers in assessing LLM use in HEOR. Methods. The ELEVATE AI LLMs framework was developed through a targeted review of existing guidelines and evaluation frameworks. The framework comprises ten evaluation domains, including model characteristics, accuracy, comprehensiveness, and fairness. The accompanying checklist operationalizes the framework. To validate the framework, we applied it to two published studies, demonstrating its usability across different HEOR tasks. Results. The ELEVATE AI LLMs framework provides a comprehensive structure for evaluating LLM-assisted research, while the checklist facilitates practical application. Validation of the framework and checklist on studies of systematic literature reviews and health economic modeling highlighted their ability to identify strengths and gaps in reporting. Limitations. While the ELEVATE AI LLMs framework provides robust guidance, its broader generalizability and applicability to diverse HEOR tasks require further empirical testing. Additionally, several metrics adapted from computer science need further validation in HEOR contexts. Conclusion. The ELEVATE AI LLMs framework and checklist fill a critical gap in HEOR by offering structured guidance for evaluating LLM-assisted research. By promoting transparency, accuracy, and reproducibility, they aim to standardize and improve the integration of LLMs into HEOR, ensuring their outputs meet the field's rigorous standards.

While LLMs have shown great success in financial tasks like stock prediction and question answering, their application in fully automating Equity Research Report generation remains uncharted territory. In this paper, we formulate the Equity Research Report (ERR) Generation task for the first time. To address the data scarcity and the evaluation metrics absence, we present an open-source evaluation benchmark for ERR generation - FinRpt. We frame a Dataset Construction Pipeline that integrates 7 financial data types and produces a high-quality ERR dataset automatically, which could be used for model training and evaluation. We also introduce a comprehensive evaluation system including 11 metrics to assess the generated ERRs. Moreover, we propose a multi-agent framework specifically tailored to address this task, named FinRpt-Gen, and train several LLM-based agents on the proposed datasets using Supervised Fine-Tuning and Reinforcement Learning. Experimental results indicate the data quality and metrics effectiveness of the benchmark FinRpt and the strong performance of FinRpt-Gen, showcasing their potential to drive innovation in the ERR generation field. All code and datasets are publicly available.

Chest Xray imaging is a widely used diagnostic tool in modern medicine, and its high utilization creates substantial workloads for radiologists. To alleviate this burden, vision language models are increasingly applied to automate Chest Xray radiology report generation (CXRRRG), aiming for clinically accurate descriptions while reducing manual effort. Conventional approaches, however, typically rely on single images, failing to capture the longitudinal context necessary for producing clinically faithful comparison statements. Recently, growing attention has been directed toward incorporating longitudinal data into CXR RRG, enabling models to leverage historical studies in ways that mirror radiologists diagnostic workflows. Nevertheless, existing surveys primarily address single image CXRRRG and offer limited guidance for longitudinal settings, leaving researchers without a systematic framework for model design. To address this gap, this survey provides the first comprehensive review of longitudinal radiology report generation (LRRG). Specifically, we examine dataset construction strategies, report generation architectures alongside longitudinally tailored designs, and evaluation protocols encompassing both longitudinal specific measures and widely used benchmarks. We further summarize LRRG methods performance, alongside analyses of different ablation studies, which collectively highlight the critical role of longitudinal information and architectural design choices in improving model performance. Finally, we summarize five major limitations of current research and outline promising directions for future development, aiming to lay a foundation for advancing this emerging field.

With breakthroughs in large-scale modeling, the Segment Anything Model (SAM) and its extensions have been attempted for applications in various underwater visualization tasks in marine sciences, and have had a significant impact on the academic community. Recently, Meta has further developed the Segment Anything Model 2 (SAM2), which significantly improves running speed and segmentation accuracy compared to its predecessor. This report aims to explore the potential of SAM2 in marine science by evaluating it on the underwater instance segmentation benchmark datasets UIIS and USIS10K. The experiments show that the performance of SAM2 is extremely dependent on the type of user-provided prompts. When using the ground truth bounding box as prompt, SAM2 performed excellently in the underwater instance segmentation domain. However, when running in automatic mode, SAM2's ability with point prompts to sense and segment underwater instances is significantly degraded. It is hoped that this paper will inspire researchers to further explore the SAM model family in the underwater domain. The results and evaluation codes in this paper are available at https://github.com/LiamLian0727/UnderwaterSAM2Eval.

Large language models (LLMs) have revolutionized artificial intelligence by enabling complex reasoning capabilities. While recent advancements in reinforcement learning (RL) have primarily focused on domain-specific reasoning tasks (e.g., mathematics or code generation), real-world reasoning scenarios often require models to handle diverse and complex environments that narrow-domain benchmarks cannot fully capture. To address this gap, we present InternBootcamp, an open-source framework comprising 1000+ domain-diverse task environments specifically designed for LLM reasoning research. Our codebase offers two key functionalities: (1) automated generation of unlimited training/testing cases with configurable difficulty levels, and (2) integrated verification modules for objective response evaluation. These features make InternBootcamp fundamental infrastructure for RL-based model optimization, synthetic data generation, and model evaluation. Although manually developing such a framework with enormous task coverage is extremely cumbersome, we accelerate the development procedure through an automated agent workflow supplemented by manual validation protocols, which enables the task scope to expand rapidly. % With these bootcamps, we further establish Bootcamp-EVAL, an automatically generated benchmark for comprehensive performance assessment. Evaluation reveals that frontier models still underperform in many reasoning tasks, while training with InternBootcamp provides an effective way to significantly improve performance, leading to our 32B model that achieves state-of-the-art results on Bootcamp-EVAL and excels on other established benchmarks. In particular, we validate that consistent performance gains come from including more training tasks, namely task scaling, over two orders of magnitude, offering a promising route towards capable reasoning generalist.

Physicians now pose millions of clinical questions to AI tools each week, yet these tools are evaluated largely on hypothetical or exam-style questions, not those actually asked in practice. We report a blinded evaluation built on 620 Real-world Point-Of-Care Queries (Real-POCQi) submitted to the OpenEvidence (OE) platform by physicians spanning 30 specialties, as well as 187 questions from HealthBench. 149 practicing physicians across 36 states made head-to-head comparisons between answers from three frontier general-purpose models (Claude Opus 4.8, Gemini 3.1 Pro, and GPT-5.5) and a specialized clinical tool (OE), with graders matched to each question's specialty. When comparing answers along five dimensions relevant to clinical decision support -- accuracy, clinical utility, source quality, verifiability, & completeness -- physicians scored the specialized tool highest on all axes; in the primary analysis on Real-POCQi, win differences (margins between win and loss rates) ranged from 25 to 39 percentage points (p<0.001). Results remained consistent in sensitivity analyses stratifying by citation display, answer length, OE-user status, and Real-POCQi versus HealthBench. In parallel, LLM judges were found to systematically differ from expert judges, though both generally agreed on the best model. These findings underscore two conclusions: (i) AI tool evaluations should reflect real-world query distributions and use expert judges that mirror the specialization defining modern medicine and (ii) the consistent advantage of the specialized tool over general-purpose models does not necessarily mean that the latter cannot serve similar purposes, but that targeted engineering and customization can yield meaningful gains in performance for its users. We release Real-POCQi as a public benchmark, as well as the prespecified statistical analysis for reproducing results of this study.

This paper investigates the effectiveness of small language models (SLMs) for agentic tasks (function/tool/API calling) with a focus on running agents on edge devices without reliance on cloud infrastructure. We evaluate SLMs using the Berkeley Function Calling Leaderboard (BFCL) framework and describe parameter-driven optimization strategies that include supervised fine-tuning (SFT), parameter-efficient fine-tuning (PEFT), reinforcement learning (RL)-based optimization, preference alignment via Direct Preference Optimization (DPO), and hybrid methods. We report results for models including TinyAgent, TinyLlama, Qwen, and xLAM across BFCL categories (simple, multiple, parallel, parallel-multiple, and relevance detection), both in live and non-live settings, and in multi-turn evaluations. We additionally detail a DPO training pipeline constructed from AgentBank data (e.g., ALFRED), including our conversion of SFT data to chosen-rejected pairs using TinyLlama responses as rejected outputs and manual validation. Our results demonstrate clear accuracy differences across model scales where medium-sized models (1-3B parameters) significantly outperform ultra-compact models (<1B parameters), achieving up to 65.74% overall accuracy, and 55.62% multi-turn accuracy with hybrid optimization. This study highlights the importance of hybrid optimization strategies that enable small language models to deliver accurate, efficient, and stable agentic AI on edge devices, making privacy-preserving, low-latency autonomous agents practical beyond the cloud.

The absence of transparency and explainability hinders the clinical adoption of Machine learning (ML) algorithms. Although various methods of explainable artificial intelligence (XAI) have been suggested, there is a lack of literature that delves into their practicality and assesses them based on criteria that could foster trust in clinical environments. To address this gap this study evaluates two popular XAI methods used for explaining predictive models in the healthcare context in terms of whether they (i) generate domain-appropriate representation, i.e. coherent with respect to the application task, (ii) impact clinical workflow and (iii) are consistent. To that end, explanations generated at the cohort and patient levels were analysed. The paper reports the first benchmarking of the XAI methods applied to risk prediction models obtained by evaluating the concordance between generated explanations and the trigger of a future clinical deterioration episode recorded by the data collection system. We carried out an analysis using two Electronic Medical Records (EMR) datasets sourced from Australian major hospitals. The findings underscore the limitations of state-of-the-art XAI methods in the clinical context and their potential benefits. We discuss these limitations and contribute to the theoretical development of trustworthy XAI solutions where clinical decision support guides the choice of intervention by suggesting the pattern or drivers for clinical deterioration in the future.

The rapid increase of computed tomography (CT) scans and their time-consuming manual analysis have created an urgent need for robust automated analysis techniques in clinical settings. These aim to assist radiologists and help them managing their growing workload. Existing methods typically generate entire reports directly from 3D CT images, without explicitly focusing on observed abnormalities. This unguided approach often results in repetitive content or incomplete reports, failing to prioritize anomaly-specific descriptions. We propose a new anomaly-guided report generation model, which first predicts abnormalities and then generates targeted descriptions for each. Evaluation on a public dataset demonstrates significant improvements in report quality and clinical relevance. We extend our work by conducting an ablation study to demonstrate its effectiveness.

This report presents EuroLLM-9B, a large language model trained from scratch to support the needs of European citizens by covering all 24 official European Union languages and 11 additional languages. EuroLLM addresses the issue of European languages being underrepresented and underserved in existing open large language models. We provide a comprehensive overview of EuroLLM-9B's development, including tokenizer design, architectural specifications, data filtering, and training procedures. We describe the pre-training data collection and filtering pipeline, including the creation of EuroFilter, an AI-based multilingual filter, as well as the design of EuroBlocks-Synthetic, a novel synthetic dataset for post-training that enhances language coverage for European languages. Evaluation results demonstrate EuroLLM-9B's competitive performance on multilingual benchmarks and machine translation tasks, establishing it as the leading open European-made LLM of its size. To support open research and adoption, we release all major components of this work, including the base and instruction-tuned models, the EuroFilter classifier, and the synthetic post-training dataset.

The LiveRAG Challenge at SIGIR 2025, held between March and May 2025, provided a competitive platform for advancing Retrieval-Augmented Generation (RAG) technologies. Participants from academia and industry were invited to develop a RAG-based question-answering system using a fixed corpus (Fineweb-10BT) and a common open-source LLM (Falcon3-10B-Instruct). The goal was to facilitate challenging comparisons of retrieval and prompting strategies. During the Live Challenge Day, 70 teams from 27 different countries provided answers and supportive information to 500 unseen questions within a strict two-hour time window. Evaluation was conducted in two stages: first an automated LLM-as-a-judge approach was used to compute correctness and faithfulness score, then a manual review of top ranked submissions was conducted. The finalists were announced on June 12, 2025, with prizes awarded during the LiveRAG Workshop at SIGIR 2025 in Padua, Italy.

This paper presents Step-Audio~2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent audio encoder and reasoning-centric reinforcement learning (RL), Step-Audio 2 achieves promising performance in automatic speech recognition (ASR) and audio understanding. To facilitate genuine end-to-end speech conversation, Step-Audio 2 incorporates the generation of discrete audio tokens into language modeling, significantly enhancing its responsiveness to paralinguistic information such as speaking styles and emotions. To effectively leverage the rich textual and acoustic knowledge in real-world data, Step-Audio 2 integrates retrieval-augmented generation (RAG) and is able to call external tools such as web search to mitigate hallucination and audio search to switch timbres. Trained on millions of hours of speech and audio data, Step-Audio 2 delivers intelligence and expressiveness across diverse conversational scenarios. Evaluation results demonstrate that Step-Audio 2 achieves state-of-the-art performance on various audio understanding and conversational benchmarks compared to other open-source and commercial solutions. Please visit https://github.com/stepfun-ai/Step-Audio2 for more information.

Safe and trustworthy use of Large Language Models (LLM) in the processing of healthcare documents and scientific papers could substantially help clinicians, scientists and policymakers in overcoming information overload and focusing on the most relevant information at a given moment. Retrieval Augmented Generation (RAG) is a promising method to leverage the potential of LLMs while enhancing the accuracy of their outcomes. This report assesses the potentials and shortcomings of such approaches in the automatic knowledge synthesis of different types of documents in the health domain. To this end, it describes: (1) an internally developed proof of concept pipeline that employs state-of-the-art practices to deliver safe and trustable analysis for healthcare documents and scientific papers called RAGEv (Retrieval Augmented Generation Evaluation); (2) a set of evaluation tools for LLM-based document retrieval and generation; (3) a benchmark dataset to verify the accuracy and veracity of the results called RAGEv-Bench. It concludes that careful implementations of RAG techniques could minimize most of the common problems in the use of LLMs for document processing in the health domain, obtaining very high scores both on short yes/no answers and long answers. There is a high potential for incorporating it into the day-to-day work of policy support tasks, but additional efforts are required to obtain a consistent and trustworthy tool.

We present Step-Audio-EditX, the first open-source LLM-based audio model excelling at expressive and iterative audio editing encompassing emotion, speaking style, and paralinguistics alongside robust zero-shot text-to-speech (TTS) capabilities.Our core innovation lies in leveraging only large-margin synthetic data, which circumvents the need for embedding-based priors or auxiliary modules. This large-margin learning approach enables both iterative control and high expressivity across voices, and represents a fundamental pivot from the conventional focus on representation-level disentanglement. Evaluation results demonstrate that Step-Audio-EditX surpasses both MiniMax-2.6-hd and Doubao-Seed-TTS-2.0 in emotion editing and other fine-grained control tasks.

As agent systems move into increasingly diverse execution settings, trajectory-level safety evaluation and diagnosis require benchmarks that evolve with them. ATBench is a diverse and realistic agent trajectory benchmark for safety evaluation and diagnosis. This report presents ATBench-Claw and ATBench-CodeX, two domain-customized extensions that carry ATBench into the OpenClaw and OpenAI Codex / Codex-runtime settings. The key adaptation mechanism is to analyze each new setting, customize the three-dimensional Safety Taxonomy over risk source, failure mode, and real-world harm, and then use that customized taxonomy to define the benchmark specification consumed by the shared ATBench construction pipeline. This extensibility matters because agent frameworks remain relatively stable at the architectural level even as their concrete execution settings, tool ecosystems, and product capabilities evolve quickly. Concretely, ATBench-Claw targets OpenClaw-sensitive execution chains over tools, skills, sessions, and external actions, while ATBench-CodeX targets trajectories in the OpenAI Codex / Codex-runtime setting over repositories, shells, patches, dependencies, approvals, and runtime policy boundaries. Our emphasis therefore falls on taxonomy customization, domain-specific risk coverage, and benchmark design under a shared ATBench generation framework.

This report presents a comparative evaluation of DKnownAI Guard in AI agent security scenarios, benchmarked against three competing products: AWS Bedrock Guardrails, Azure Content Safety, and Lakera Guard. Using human annotation as the ground truth, we assess each guardrail's ability to detect two categories of risks: threats to the agent itself (e.g., instruction override, indirect injection, tool abuse) and requests intended to elicit harmful content (e.g., hate speech, pornography, violence). Evaluation results demonstrate that DKnownAI Guard achieves the highest recall rate at 96.5\% and ranks first in true negative rate (TNR) at 90.4\%, delivering the best overall performance among all evaluated guardrails.

Predicting a football match before kickoff requires more than knowing past results: a model must use changing information and make a clear prediction before the answer is available. We present WorldCupArena, a dynamic benchmark for language models and deep-research agents. The 2026 FIFA World Cup is its first evaluation, and the same process can be reused for future leagues and cups. Before each match, a model either receives a common evidence package or searches for information itself. It predicts the result and score, likely players and events, match statistics, and the outcome of the competition. After the match, these predictions are compared with the recorded result. We report result accuracy, exact-score accuracy, and a scoreline score that gives some credit when a predicted score is close but not exact, together with scores for the other prediction tasks. Across 104 matches and 13 systems, models with similar result accuracy differ more clearly on detailed predictions. Compared with betting-market and human-fan baselines, the best system shows only small gains in result and exact-score accuracy, but a clearer gain in Scoreline. New schedules can be added as they begin, allowing the benchmark to evaluate future models without using outcomes that are already known. Code, prompts, predictions, and evaluation scripts are open sourced at https://github.com/wzk1015/WorldCupArena.

This paper presents LLM-jp-4, a family of Japanese sovereign large language models (LLMs) developed with an emphasis on transparency, reproducibility, and practical usability. LLM-jp-4 comprises an 8B dense model and a 32B-A3B mixture-of-experts model, both trained from scratch on approximately 12 trillion tokens. To support independent verification and reproduction, we establish explicit criteria for selecting training data, external models, and software, and make the development process publicly available. Evaluation results demonstrate substantial improvements over previous LLM-jp models and competitive performance against open-weight models of similar scale. By documenting the development principles, training procedures, and empirical findings of LLM-jp-4, we aim to provide a reference for future sovereign AI development.

The advent of Deep Research agents has substantially reduced the time required for conducting extensive research tasks. However, these tasks inherently demand rigorous standards of factual accuracy and comprehensiveness, necessitating thorough evaluation before widespread adoption. In this paper, we propose ReportBench, a systematic benchmark designed to evaluate the content quality of research reports generated by large language models (LLMs). Our evaluation focuses on two critical dimensions: (1) the quality and relevance of cited literature, and (2) the faithfulness and veracity of the statements within the generated reports. ReportBench leverages high-quality published survey papers available on arXiv as gold-standard references, from which we apply reverse prompt engineering to derive domain-specific prompts and establish a comprehensive evaluation corpus. Furthermore, we develop an agent-based automated framework within ReportBench that systematically analyzes generated reports by extracting citations and statements, checking the faithfulness of cited content against original sources, and validating non-cited claims using web-based resources. Empirical evaluations demonstrate that commercial Deep Research agents such as those developed by OpenAI and Google consistently generate more comprehensive and reliable reports than standalone LLMs augmented with search or browsing tools. However, there remains substantial room for improvement in terms of the breadth and depth of research coverage, as well as factual consistency. The complete code and data will be released at the following link: https://github.com/ByteDance-BandAI/ReportBench

Evaluation for automatic crisis reporting should measure what practitioners need, not what is convenient to compare. Through LLM-assisted, author-approved content analysis, we derive a 15-slot information schema from professional humanitarian situation reports using qualitative content analysis, then evaluate 121 human and 261 LLM-generated reports across five disasters and three hazard types. Under google/gemini-3.7-flash on Cyclone Idai, the best machine arm is nominally above the empirical human ceiling (0.827 vs. 0.821), but the difference is statistically indistinguishable from zero (95\% bootstrap CI [-.049,.059]; permutation p=.852), and the ordering does not replicate under openai/gpt-5.6-luna. On a blind 100-item Idai sample, the author agrees with the Gemini judge at 0.910 accuracy and unweighted Cohen's κ=.799. All four judges clear the plan's raw-agreement criterion of .7; only Gemini reaches .7 on chance-corrected κ. Across the three primary events, machine reports reproduce 5.4-11.0% of same-day official figures. Across those same events, raw exact-number matching links 14.3-19.6% of official figures and 85.4-90.1% of machine figures to the social stream; manual audit confirms 45/50 declared absences, 4/25 official matches, and 24/25 machine matches semantically. The issuing-provenance gap is positive in all 12 observed event-judge cells: report date, organisation, series, and authority were not supplied at professional-report coverage in any cell. On the three primary events, ROUGE-L is uninformative, BERTScore is negatively associated with completeness after multiplicity correction, and a generic LLM judge changes sign.

Generating clinical reports from raw recordings such as X-rays and electroencephalogram (EEG) is an essential and routine task for doctors. However, it is often time-consuming to write accurate and detailed reports. Most existing methods try to generate the whole reports from the raw input with limited success because 1) generated reports often contain errors that need manual review and correction, 2) it does not save time when doctors want to write additional information into the report, and 3) the generated reports are not customized based on individual doctors' preference. We propose {\it CL}inic{\it A}l {\it R}eport {\it A}uto-completion (CLARA), an interactive method that generates reports in a sentence by sentence fashion based on doctors' anchor words and partially completed sentences. CLARA searches for most relevant sentences from existing reports as the template for the current report. The retrieved sentences are sequentially modified by combining with the input feature representations to create the final report. In our experimental evaluation, CLARA achieved 0.393 CIDEr and 0.248 BLEU-4 on X-ray reports and 0.482 CIDEr and 0.491 BLEU-4 for EEG reports for sentence-level generation, which is up to 35% improvement over the best baseline. Also via our qualitative evaluation, CLARA is shown to produce reports which have a significantly higher level of approval by doctors in a user study (3.74 out of 5 for CLARA vs 2.52 out of 5 for the baseline).

Large Language Models (LLMs) have become ubiquitous across various domains, transforming the way we interact with information and conduct research. However, most high-performing LLMs remain confined behind proprietary walls, hindering scientific progress. Most open-source LLMs, on the other hand, are limited in their ability to support longer sequence lengths, which is a key requirement for many tasks that require inference over an input context. To address this, we have trained XGen, a series of 7B parameter models on up to 8K sequence length for up to 1.5T tokens. We have also finetuned the XGen models on public-domain instructional data, creating their instruction-tuned counterparts (XGen-Inst). We open-source our models for both research advancements and commercial applications. Our evaluation on standard benchmarks shows that XGen models achieve comparable or better results when compared with state-of-the-art open-source LLMs. Our targeted evaluation on long sequence modeling tasks shows the benefits of our 8K-sequence models over 2K-sequence open-source LLMs.

Breast ultrasound (BUS) is a critical diagnostic tool in the field of breast imaging, aiding in the early detection and characterization of breast abnormalities. Interpreting breast ultrasound images commonly involves creating comprehensive medical reports, containing vital information to promptly assess the patient's condition. However, the ultrasound imaging system necessitates capturing multiple images of various parts to compile a single report, presenting a time-consuming challenge. To address this problem, we propose the integration of multiple image analysis tools through a LangChain using Large Language Models (LLM), into the breast reporting process. Through a combination of designated tools and text generation through LangChain, our method can accurately extract relevant features from ultrasound images, interpret them in a clinical context, and produce comprehensive and standardized reports. This approach not only reduces the burden on radiologists and healthcare professionals but also enhances the consistency and quality of reports. The extensive experiments shows that each tools involved in the proposed method can offer qualitatively and quantitatively significant results. Furthermore, clinical evaluation on the generated reports demonstrates that the proposed method can make report in clinically meaningful way.

In software development, bug report reproduction is a challenging task. This paper introduces ReBL, a novel feedback-driven approach that leverages GPT-4, a large-scale language model, to automatically reproduce Android bug reports. Unlike traditional methods, ReBL bypasses the use of Step to Reproduce (S2R) entities. Instead, it leverages the entire textual bug report and employs innovative prompts to enhance GPT's contextual reasoning. This approach is more flexible and context-aware than the traditional step-by-step entity matching approach, resulting in improved accuracy and effectiveness. In addition to handling crash reports, ReBL has the capability of handling non-crash bug reports. Our evaluation of 96 Android bug reports (73 crash and 23 non-crash) demonstrates that ReBL successfully reproduced 90.63% of these reports, averaging only 74.98 seconds per bug report. Additionally, ReBL outperformed three existing tools in both success rate and speed.

This work introduces Salamandra, a suite of open-source decoder-only large language models available in three different sizes: 2, 7, and 40 billion parameters. The models were trained from scratch on highly multilingual data that comprises text in 35 European languages and code. Our carefully curated corpus is made exclusively from open-access data compiled from a wide variety of sources. Along with the base models, supplementary checkpoints that were fine-tuned on public-domain instruction data are also released for chat applications. Additionally, we also share our preliminary experiments on multimodality, which serve as proof-of-concept to showcase potential applications for the Salamandra family. Our extensive evaluations on multilingual benchmarks reveal that Salamandra has strong capabilities, achieving competitive performance when compared to similarly sized open-source models. We provide comprehensive evaluation results both on standard downstream tasks as well as key aspects related to bias and safety.With this technical report, we intend to promote open science by sharing all the details behind our design choices, data curation strategy and evaluation methodology. In addition to that, we deviate from the usual practice by making our training and evaluation scripts publicly accessible. We release all models under a permissive Apache 2.0 license in order to foster future research and facilitate commercial use, thereby contributing to the open-source ecosystem of large language models.

Large language models (LLMs) have demonstrated strong capabilities in language understanding, generation, and reasoning, yet their potential in finance remains underexplored due to the complexity and specialization of financial knowledge. In this work, we report the development of the Baichuan4-Finance series, including a comprehensive suite of foundational Baichuan4-Finance-Base and an aligned language model Baichuan4-Finance, which are built upon Baichuan4-Turbo base model and tailored for finance domain. Firstly, we have dedicated significant effort to building a detailed pipeline for improving data quality. Moreover, in the continual pre-training phase, we propose a novel domain self-constraint training strategy, which enables Baichuan4-Finance-Base to acquire financial knowledge without losing general capabilities. After Supervised Fine-tuning and Reinforcement Learning from Human Feedback and AI Feedback, the chat model Baichuan4-Finance is able to tackle various financial certification questions and real-world scenario applications. We evaluate Baichuan4-Finance on many widely used general datasets and two holistic financial benchmarks. The evaluation results show that Baichuan4-Finance-Base surpasses almost all competitive baselines on financial tasks by significant margins without sacrificing performance on general LLM benchmarks. At the same time, Baichuan4-Finance demonstrates even more impressive performance on financial application scenarios, showcasing its potential to foster community innovation in the financial LLM field.

We present Kimi-Audio, an open-source audio foundation model that excels in audio understanding, generation, and conversation. We detail the practices in building Kimi-Audio, including model architecture, data curation, training recipe, inference deployment, and evaluation. Specifically, we leverage a 12.5Hz audio tokenizer, design a novel LLM-based architecture with continuous features as input and discrete tokens as output, and develop a chunk-wise streaming detokenizer based on flow matching. We curate a pre-training dataset that consists of more than 13 million hours of audio data covering a wide range of modalities including speech, sound, and music, and build a pipeline to construct high-quality and diverse post-training data. Initialized from a pre-trained LLM, Kimi-Audio is continual pre-trained on both audio and text data with several carefully designed tasks, and then fine-tuned to support a diverse of audio-related tasks. Extensive evaluation shows that Kimi-Audio achieves state-of-the-art performance on a range of audio benchmarks including speech recognition, audio understanding, audio question answering, and speech conversation. We release the codes, model checkpoints, as well as the evaluation toolkits in https://github.com/MoonshotAI/Kimi-Audio.

We present Bielik 11B v2, a state-of-the-art language model optimized for Polish text processing. Built on the Mistral 7B v0.2 architecture and scaled to 11B parameters using depth up-scaling, this model demonstrates exceptional performance across Polish language benchmarks while maintaining strong cross-lingual capabilities. We introduce two key technical innovations: Weighted Instruction Cross-Entropy Loss, which optimizes learning across diverse instruction types by assigning quality-based weights to training examples, and Adaptive Learning Rate, which dynamically adjusts based on context length. Comprehensive evaluation across multiple benchmarks demonstrates that Bielik 11B v2 outperforms many larger models, including those with 2-6 times more parameters, and significantly surpasses other specialized Polish language models on tasks ranging from linguistic understanding to complex reasoning. The model's parameter efficiency and extensive quantization options enable deployment across various hardware configurations, advancing Polish language AI capabilities and establishing new benchmarks for resource-efficient language modeling in less-represented languages.

Even though large language models are becoming increasingly capable, it is still unreasonable to expect them to excel at tasks that are under-represented on the Internet. Leveraging LLMs for specialized applications, particularly in niche programming languages and private domains, remains challenging and largely unsolved. In this work, we address this gap by presenting a comprehensive, open-source approach for adapting LLMs to the Q programming language, a popular tool in quantitative finance that is much less present on the Internet compared to Python, C, Java, and other ``mainstream" languages and is therefore not a strong suit of general-purpose AI models. We introduce a new Leetcode style evaluation dataset for Q, benchmark major frontier models on the dataset, then do pretraining, supervised fine tuning, and reinforcement learning to train a suite of reasoning and non-reasoning models based on the Qwen-2.5 series, spanning five parameter sizes (1.5B, 3B, 7B, 14B, 32B). Our best model achieves a pass@1 accuracy of 59 percent on our Q benchmark, surpassing the best-performing frontier model, Claude Opus-4 by 29.5 percent. Additionally, all models, even our 1.5B model, outperform GPT-4.1 on this task. In addition to releasing models, code, and data, we provide a detailed blueprint for dataset construction, model pretraining, supervised fine-tuning, and reinforcement learning. Our methodology is broadly applicable, and we discuss how these techniques can be extended to other tasks, including those where evaluation may rely on soft or subjective signals.

The development of autonomous agents for graphical user interfaces (GUIs) presents major challenges in artificial intelligence. While recent advances in native agent models have shown promise by unifying perception, reasoning, action, and memory through end-to-end learning, open problems remain in data scalability, multi-turn reinforcement learning (RL), the limitations of GUI-only operation, and environment stability. In this technical report, we present UI-TARS-2, a native GUI-centered agent model that addresses these challenges through a systematic training methodology: a data flywheel for scalable data generation, a stabilized multi-turn RL framework, a hybrid GUI environment that integrates file systems and terminals, and a unified sandbox platform for large-scale rollouts. Empirical evaluation demonstrates that UI-TARS-2 achieves significant improvements over its predecessor UI-TARS-1.5. On GUI benchmarks, it reaches 88.2 on Online-Mind2Web, 47.5 on OSWorld, 50.6 on WindowsAgentArena, and 73.3 on AndroidWorld, outperforming strong baselines such as Claude and OpenAI agents. In game environments, it attains a mean normalized score of 59.8 across a 15-game suite-roughly 60% of human-level performance-and remains competitive with frontier proprietary models (e.g., OpenAI o3) on LMGame-Bench. Additionally, the model can generalize to long-horizon information-seeking tasks and software engineering benchmarks, highlighting its robustness across diverse agent tasks. Detailed analyses of training dynamics further provide insights into achieving stability and efficiency in large-scale agent RL. These results underscore UI-TARS-2's potential to advance the state of GUI agents and exhibit strong generalization to real-world interactive scenarios.

We present Foundation-Sec-8B-Reasoning, the first open-source native reasoning model for cybersecurity. Built upon our previously released Foundation-Sec-8B base model (derived from Llama-3.1-8B-Base), the model is trained through a two-stage process combining supervised fine-tuning (SFT) and reinforcement learning from verifiable rewards (RLVR). Our training leverages proprietary reasoning data spanning cybersecurity analysis, instruction-following, and mathematical reasoning. Evaluation across 10 cybersecurity benchmarks and 10 general-purpose benchmarks demonstrates performance competitive with significantly larger models on cybersecurity tasks while maintaining strong general capabilities. The model shows effective generalization on multi-hop reasoning tasks and strong safety performance when deployed with appropriate system prompts and guardrails. This work demonstrates that domain-specialized reasoning models can achieve strong performance on specialized tasks while maintaining broad general capabilities. We release the model publicly at https://huggingface.co/fdtn-ai/Foundation-Sec-8B-Reasoning.

While full-duplex speech agents enable natural, low-latency interaction by speaking and listening simultaneously, their consistency and task performance in multi-turn settings remain underexplored. We introduce Full-Duplex-Bench-v2 (FDB-v2), a streaming framework that integrates with an automated examiner that enforces staged goals under two pacing setups (Fast vs. Slow). FDB-v2 covers four task families: daily, correction, entity tracking, and safety. We report turn-taking fluency, multi-turn instruction following, and task-specific competence. The framework is extensible, supporting both commercial APIs and open source models. When we test full-duplex systems with FDB-v2, they often get confused when people talk at the same time, struggle to handle corrections smoothly, and sometimes lose track of who or what is being talked about. Through an open-sourced, standardized streaming protocol and a task set, FDB-v2 makes it easy to extend to new task families, allowing the community to tailor and accelerate evaluation of multi-turn full-duplex systems.

Knowledge Graph (KG) plays a crucial role in Medical Report Generation (MRG) because it reveals the relations among diseases and thus can be utilized to guide the generation process. However, constructing a comprehensive KG is labor-intensive and its applications on the MRG process are under-explored. In this study, we establish a complete KG on chest X-ray imaging that includes 137 types of diseases and abnormalities. Based on this KG, we find that the current MRG data sets exhibit a long-tailed problem in disease distribution. To mitigate this problem, we introduce a novel augmentation strategy that enhances the representation of disease types in the tail-end of the distribution. We further design a two-stage MRG approach, where a classifier is first trained to detect whether the input images exhibit any abnormalities. The classified images are then independently fed into two transformer-based generators, namely, ``disease-specific generator" and ``disease-free generator" to generate the corresponding reports. To enhance the clinical evaluation of whether the generated reports correctly describe the diseases appearing in the input image, we propose diverse sensitivity (DS), a new metric that checks whether generated diseases match ground truth and measures the diversity of all generated diseases. Results show that the proposed two-stage generation framework and augmentation strategies improve DS by a considerable margin, indicating a notable reduction in the long-tailed problem associated with under-represented diseases.

We present Qwen-Image-2.0-RL, a post-training pipeline that applies reinforcement learning from human feedback (RLHF) and on-policy distillation (OPD) to improve both the visual quality and instruction-following capability of the Qwen-Image-2.0 diffusion model. To provide reliable reward signals, we construct task-specific composite reward models by fine-tuning vision-language models with a pointwise scoring paradigm and chain-of-thought reasoning. For text-to-image generation, the reward models cover alignment, aesthetics, and portrait fidelity dimensions. For image editing tasks, the reward system addresses instruction-following accuracy and face identity preservation. Building on this reward system, we develop a scalable GRPO-based RL training framework, incorporating a hybrid classifier-free guidance (CFG) strategy to preserve pre-trained knowledge, prompt curation via intra-group reward range filtering, and per-category reward weight calibration. To merge the task-specialized RL policies for T2I and editing, we propose on-policy distillation as the final training stage, which consolidates multiple teachers into a single student model through trajectory-level velocity matching. Extensive evaluation shows that Qwen-Image-2.0-RL achieves 57.84 overall score on Qwen-Image-Bench (+2.61 over the base model), Elo ratings of 1193 in text-to-image arena (+78) and 1349 in image edit arena (+93), demonstrating consistent gains in aesthetic quality, prompt adherence, and editing accuracy.

Humans demonstrate remarkable abilities to predict physical events in complex scenes. Two classes of models for physical scene understanding have recently been proposed: "Intuitive Physics Engines", or IPEs, which posit that people make predictions by running approximate probabilistic simulations in causal mental models similar in nature to video-game physics engines, and memory-based models, which make judgments based on analogies to stored experiences of previously encountered scenes and physical outcomes. Versions of the latter have recently been instantiated in convolutional neural network (CNN) architectures. Here we report four experiments that, to our knowledge, are the first rigorous comparisons of simulation-based and CNN-based models, where both approaches are concretely instantiated in algorithms that can run on raw image inputs and produce as outputs physical judgments such as whether a stack of blocks will fall. Both approaches can achieve super-human accuracy levels and can quantitatively predict human judgments to a similar degree, but only the simulation-based models generalize to novel situations in ways that people do, and are qualitatively consistent with systematic perceptual illusions and judgment asymmetries that people show.

We introduce DiffusionGemma, an experimental open-weight language model that uses discrete diffusion to generate text at exceptionally high speed. Rather than decoding one token at a time, DiffusionGemma iteratively refines blocks of 256 tokens in parallel, avoiding the sequential decoding bottleneck of conventional autoregressive (AR) large language models. Instead of training from scratch, we obtain DiffusionGemma by fine-tuning the mixture-of-experts Gemma 4 model with 3.8B activated and 25.2B total parameters. Our compute-efficient two-stage training pipeline uses fewer than 10% of the starting AR model's total training token budget. The first stage uses supervised fine-tuning to teach bidirectional denoising, while the second stage combines reinforcement learning with sampler distillation to jointly improve generation quality and inference efficiency. DiffusionGemma establishes a new Pareto frontier for the trade-off between generation speed and model capability. Averaged across our full evaluation suite, it generates around 20 tokens per forward pass and achieves roughly 1,500 output tokens per second on a single NVIDIA H100 GPU, which is substantially faster than AR models even with state-of-the-art speculative decoding. DiffusionGemma also retains the starting model's support for thinking mode, multimodal inputs, and long contexts. Despite diffusion fine-tuning, it remains capable of AR generation with only minor performance degradation, suggesting a path toward hybrid diffusion-AR decoding.

We introduce Kaggle Game Arena, an open and ever-expanding platform to evaluate large language models (LLMs) through competitive games. Different from static benchmarks, game arena enables models to play head-to-head matchups in structured environments where the gameplay strength naturally increases as models evolve, preventing performance saturation. This technical report details the infrastructure behind Game Arena and describes the three pilot game environments: Chess, Poker, and Werewolf. These environments span perfect information, imperfect information, and multiplayer game settings, enabling a systematic study of models' strategic planning, adaptation, and robustness under uncertainty. For each game, we provide a detailed description of the environment, evaluation metrics, and results from running full competitions across models. Through robust infrastructure and large-scale ground-truth based evaluation, Game Arena ensures reproducibility, transparency and generalizability to new games and variants over time.

Automated generation of clinically accurate radiology reports can improve patient care. Previous report generation methods that rely on image captioning models often generate incoherent and incorrect text due to their lack of relevant domain knowledge, while retrieval-based attempts frequently retrieve reports that are irrelevant to the input image. In this work, we propose Contrastive X-Ray REport Match (X-REM), a novel retrieval-based radiology report generation module that uses an image-text matching score to measure the similarity of a chest X-ray image and radiology report for report retrieval. We observe that computing the image-text matching score with a language-image model can effectively capture the fine-grained interaction between image and text that is often lost when using cosine similarity. X-REM outperforms multiple prior radiology report generation modules in terms of both natural language and clinical metrics. Human evaluation of the generated reports suggests that X-REM increased the number of zero-error reports and decreased the average error severity compared to the baseline retrieval approach. Our code is available at: https://github.com/rajpurkarlab/X-REM

Object removal refers to the process of erasing designated objects from an image while preserving the overall appearance, and it is one area where image inpainting is widely used in real-world applications. The performance of an object remover is quantitatively evaluated by measuring the quality of object removal results, similar to how the performance of an image inpainter is gauged. Current works reporting quantitative performance evaluations utilize original images as references. In this letter, to validate the current evaluation methods cannot properly evaluate the performance of an object remover, we create a dataset with object removal ground truth and compare the evaluations made by the current methods using original images to those utilizing object removal ground truth images. The disparities between two evaluation sets validate that the current methods are not suitable for measuring the performance of an object remover. Additionally, we propose new evaluation methods tailored to gauge the performance of an object remover. The proposed methods evaluate the performance through class-wise object removal results and utilize images without the target class objects as a comparison set. We confirm that the proposed methods can make judgments consistent with human evaluators in the COCO dataset, and that they can produce measurements aligning with those using object removal ground truth in the self-acquired dataset.

This comprehensive study evaluates the performance of OpenAI's o1-preview large language model across a diverse array of complex reasoning tasks, spanning multiple domains, including computer science, mathematics, natural sciences, medicine, linguistics, and social sciences. Through rigorous testing, o1-preview demonstrated remarkable capabilities, often achieving human-level or superior performance in areas ranging from coding challenges to scientific reasoning and from language processing to creative problem-solving. Key findings include: -83.3% success rate in solving complex competitive programming problems, surpassing many human experts. -Superior ability in generating coherent and accurate radiology reports, outperforming other evaluated models. -100% accuracy in high school-level mathematical reasoning tasks, providing detailed step-by-step solutions. -Advanced natural language inference capabilities across general and specialized domains like medicine. -Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis. -Remarkable proficiency in anthropology and geology, demonstrating deep understanding and reasoning in these specialized fields. -Strong capabilities in quantitative investing. O1 has comprehensive financial knowledge and statistical modeling skills. -Effective performance in social media analysis, including sentiment analysis and emotion recognition. The model excelled particularly in tasks requiring intricate reasoning and knowledge integration across various fields. While some limitations were observed, including occasional errors on simpler problems and challenges with certain highly specialized concepts, the overall results indicate significant progress towards artificial general intelligence.

DeepResearch agents represent a transformative AI paradigm, conducting expert-level research through sophisticated reasoning and multi-tool integration. However, evaluating these systems remains critically challenging due to open-ended research scenarios and existing benchmarks that focus on isolated capabilities rather than holistic performance. Unlike traditional LLM tasks, DeepResearch systems must synthesize diverse sources, generate insights, and present coherent findings, which are capabilities that resist simple verification. To address this gap, we introduce DeepResearch-ReportEval, a comprehensive framework designed to assess DeepResearch systems through their most representative outputs: research reports. Our approach systematically measures three dimensions: quality, redundancy, and factuality, using an innovative LLM-as-a-Judge methodology achieving strong expert concordance. We contribute a standardized benchmark of 100 curated queries spanning 12 real-world categories, enabling systematic capability comparison. Our evaluation of four leading commercial systems reveals distinct design philosophies and performance trade-offs, establishing foundational insights as DeepResearch evolves from information assistants toward intelligent research partners. Source code and data are available at: https://github.com/HKUDS/DeepResearch-Eval.

Evaluating whether text-to-image models follow explicit spatial instructions is difficult to automate. Object detectors may miss targets or return multiple plausible detections, and simple geometric tests can become ambiguous in borderline cases. Spatial evaluation is naturally a selective prediction problem, the checker may abstain when evidence is weak and report confidence so that results can be interpreted as a risk coverage tradeoff rather than a single score. We introduce SpatialBench-UC, a small, reproducible benchmark for pairwise spatial relations. The benchmark contains 200 prompts (50 object pairs times 4 relations) grouped into 100 counterfactual pairs obtained by swapping object roles. We release a benchmark package, versioned prompts, pinned configs, per-sample checker outputs, and report tables, enabling reproducible and auditable comparisons across models. We also include a lightweight human audit used to calibrate the checker's abstention margin and confidence threshold. We evaluate three baselines, Stable Diffusion 1.5, SD 1.5 BoxDiff, and SD 1.4 GLIGEN. The checker reports pass rate and coverage as well as conditional pass rates on decided samples. The results show that grounding methods substantially improve both pass rate and coverage, while abstention remains a dominant factor due mainly to missing detections.

Diffusion transformer (DiT) research on image generation has converged to a single evaluation setup: class-conditional generation on ImageNet. While methods improve the FID and related metrics, it is increasingly unclear whether they reflect real progress in generative modeling. The natural alternative, i.e., text-to-image (T2I) generation, is perceived as too costly or inconvenient to train and evaluate and is often skipped. We argue that this perception no longer holds. We introduce NanoGen, a unified DiT training and evaluation framework. NanoGen matches state-of-the-art DiT baselines on ImageNet and, with 12 lines of configuration change, also trains competitive text-to-image models. It currently supports RAE, VAE, pixel-space, and MeanFlow diffusion methods under both ImageNet and T2I setups. Under NanoGen, training T2I requires comparable compute to ImageNet. After training 21 latent diffusion models with NanoGen, we observe that method ranking shows no strong correlation between ImageNet and T2I generation: Pearson correlation is between -0.377 and -0.580 across three metrics. This suggests that a method which improves class-conditional ImageNet FID may show no corresponding improvement on T2I, clearly indicating the necessity of evaluating DiTs on both tasks. To this end, we summarize ImageNet and text-to-image results, which yields DiffusionBench, a holistic benchmark for DiT research. We recommend reporting DiffusionBench in place of ImageNet alone: methods that improve DiffusionBench are more likely to reflect broader progress.

This paper reports on a collaboration between the Directorate-General for Translation (DGT) and the European Master's in Translation (EMT) to localise the MMLU dataset into 11 European languages. Beyond creating a more inclusive benchmark for LLM evaluation, the project offers master's students authentic, project-based professional training in translation, revision, project management, and multilingual coordination, while highlighting key methodological, administrative, and workflow challenges.

The work in this paper evaluates zero-shot and few-shot large language models (LLMs) for safety-critical clinical action extraction using the CLIP discharge-note dataset, with particular emphasis on transitions of care and post-discharge patient safety. To manage the complexity of clinical documentation, we introduce a two-stage extraction framework that decomposes discharge notes, that are written in narrative form, into fine-grained, explicitly actionable clinical tasks through a staged prompting strategy. Our contributions include a systematic assessment of generative LLMs for clinical action extraction, a detailed comparison between general-purpose LLMs and task-specific supervised BERT-based models, and an analysis of annotation inconsistencies across different action categories. We show that contemporary LLMs achieve performance comparable to or exceeding supervised models on binary actionability detection, while supervised baselines retain a meaningful advantage on fine-grained multi-label category classification, despite the absence of task-specific fine-tuning and under strict data-privacy constraints. Qualitative error analysis reveals that many failures stem from misalignment between model reasoning and dataset annotation conventions, particularly in cases involving implicit clinical actions and rigid structural labeling rules. These results indicate that reported performance reflects model limitations due to lack of clinical reasoning, that is not captured by plain annotations. Labels without rationales make it impossible to distinguish clinical reasoning failures from annotation convention mismatches. Advancing clinical NLP requires reasoning-annotated datasets that document why specific spans are actionable, not merely which spans were labeled, enabling proper evaluation of model clinical understanding.

In this paper we show that reporting a single performance score is insufficient to compare non-deterministic approaches. We demonstrate for common sequence tagging tasks that the seed value for the random number generator can result in statistically significant (p < 10^-4) differences for state-of-the-art systems. For two recent systems for NER, we observe an absolute difference of one percentage point F1-score depending on the selected seed value, making these systems perceived either as state-of-the-art or mediocre. Instead of publishing and reporting single performance scores, we propose to compare score distributions based on multiple executions. Based on the evaluation of 50.000 LSTM-networks for five sequence tagging tasks, we present network architectures that produce both superior performance as well as are more stable with respect to the remaining hyperparameters.