Into the Unknown: Benchmarking AI agents on open scientific research problems Paper • 2610.19159 • Published Oct 13 • 57
Self-Evolving Coding Agents via Harness-Policy Optimization Paper • 2610.22791 • Published Oct 16 • 50
Athanor: An Agent-Native System for Autonomous Post-Training Research Paper • 2610.21055 • Published Oct 15 • 17
AgentBaton: Efficient Model Collaboration in Agentic Tasks Paper • 2610.35959 • Published 22 days ago • 26
EmbeddingGemma 2: Unified and Efficient Multimodal Representations Paper • 2610.37364 • Published 20 days ago • 38
Retriever-Free Retrieval: Navigating Documents with Decision Models Paper • 2610.35868 • Published 21 days ago • 1
Learning Heterogeneous Tactile Representation for General Dexterous Manipulation Paper • 2611.12806 • Published 7 days ago • 105
Draft in Parallel, Condition Through Depth: Adjacent Causal Injection for Speculative Decoding Paper • 2609.36173 • Published Sep 28 • 5
REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control Paper • 2610.42053 • Published 17 days ago • 19
TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving Paper • 2610.37230 • Published 20 days ago • 27
Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs Paper • 2610.36671 • Published 20 days ago • 118
AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding Paper • 2610.38678 • Published 19 days ago • 13
WebAnything: From the Wild Web to Scalable Agent Environments Paper • 2610.37786 • Published 20 days ago • 20
MiRL: Error-Targeted Reinforcement Learning for Correcting Terminal Agent Misbehaviors Paper • 2610.35697 • Published 21 days ago • 1
CausalWAM: Learning the Causes of Actions in World Action Models Paper • 2610.42096 • Published 17 days ago • 6
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning Paper • 2610.37666 • Published 20 days ago • 59
Rollback: Experience Backtracking in World Models for Policy Improvement Paper • 2610.36068 • Published 21 days ago • 54
Probing Spatial State Representations in Visual Foundation Models Paper • 2610.40636 • Published 18 days ago • 22
Harness-Model Collaboration for Long-Horizon Continual Learning Paper • 2610.34724 • Published 21 days ago • 13
More Memory, Better Videos? A Controlled Study of Visual Memory in Long-Video Generation Paper • 2610.35001 • Published 21 days ago • 17