ClawBench: Can AI Agents Complete Everyday Online Tasks? Paper • 2604.08523 • Published 14 days ago • 259
Meta-Harness: End-to-End Optimization of Model Harnesses Paper • 2603.28052 • Published 24 days ago • 19
CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery Paper • 2604.01658 • Published 21 days ago • 55
SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization Paper • 2604.02268 • Published 21 days ago • 96
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook Paper • 2604.02029 • Published 21 days ago • 144
InCoder-32B-Thinking: Industrial Code World Model for Thinking Paper • 2604.03144 • Published 20 days ago • 232
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published 20 days ago • 365
SkillX: Automatically Constructing Skill Knowledge Bases for Agents Paper • 2604.04804 • Published 17 days ago • 33
LightThinker++: From Reasoning Compression to Memory Management Paper • 2604.03679 • Published 19 days ago • 37
ClawArena: Benchmarking AI Agents in Evolving Information Environments Paper • 2604.04202 • Published 18 days ago • 37
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression Paper • 2604.04921 • Published 17 days ago • 110
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents Paper • 2604.06132 • Published 16 days ago • 117
INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling Paper • 2604.07209 • Published 15 days ago • 36