Replay, Don't Resample: Off-Policy Consolidation of Long-Horizon RL Experts Paper • 2611.24059 • Published 5 days ago • 6
The Resolution Hypothesis: Agent Evolution's Key Is Identifying Improvements Paper • 2611.23068 • Published 6 days ago • 40
VideoNexus: Video Perception Beyond the Reasoning Context Paper • 2611.21392 • Published 7 days ago • 21
Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent Paper • 2611.18397 • Published 10 days ago • 150
BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model Paper • 2611.14815 • Published 13 days ago • 57
PREEN: Exemplar-Based Color Style Transfer with Smartphone Editor Presets Paper • 2610.36896 • Published 27 days ago • 6
LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting Paper • 2611.06808 • Published 19 days ago • 38
Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents Paper • 2611.02075 • Published 22 days ago • 42
Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks? Paper • 2611.02017 • Published 22 days ago • 11
FrontierPhysics: Evaluating Agents for End-to-End Physics Research Paper • 2611.06910 • Published 19 days ago • 67
DeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers Paper • 2610.37826 • Published 24 days ago • 15
R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop Paper • 2610.22740 • Published Oct 22 • 50
AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers Paper • 2610.39663 • Published 25 days ago • 9
OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images Paper • 2610.35684 • Published 28 days ago • 53
TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving Paper • 2610.37230 • Published 27 days ago • 26
Steering Black-Box Large Language Model Agents with Pitfall Anticipation World Model Paper • 2610.29139 • Published Oct 21 • 6
Function-Space Temporal Self-Distillation for Policy Optimization Paper • 2610.19687 • Published Oct 14 • 26
BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business Paper • 2610.20424 • Published Oct 14 • 58