FrontierPhysics: Evaluating Agents for End-to-End Physics Research Paper • 2611.06910 • Published 17 days ago • 67
On the Origin and Evolution of Training-Inference Mismatch in LLM Reinforcement Learning Paper • 2610.40945 • Published 23 days ago • 11
WorldOracle: Benchmarking Action-Conditioned World Models against Real-World Executions Paper • 2610.18826 • Published Oct 13 • 3
Athanor: An Agent-Native System for Autonomous Post-Training Research Paper • 2610.21055 • Published Oct 15 • 17
MMedAgent: Learning to Use Medical Tools with Multi-modal Agent Paper • 2407.02483 • Published Jul 2, 2024 • 2