Qwen-AgentWorld: Language World Models for General Agents Paper • 2606.24597 • Published 2 days ago • 79
NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers? Paper • 2606.24530 • Published 2 days ago • 47
EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions Paper • 2606.23654 • Published 3 days ago • 71
Post-Trained MoE Can Skip Half Experts via Self-Distillation Paper • 2605.18643 • Published May 18 • 30
Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling Paper • 2605.13301 • Published May 13 • 165
FlowRL: Matching Reward Distributions for LLM Reasoning Paper • 2509.15207 • Published Sep 18, 2025 • 119