FrontierPhysics: Evaluating Agents for End-to-End Physics Research Paper • 2611.06910 • Published 1 day ago • 24
Selecting Diverse SFT Traces Improves Post-RL Generalization Paper • 2609.33780 • Published Sep 27 • 34
SPADE: Self-Play in Adaptive Synthetic Executable Environments Paper • 2608.19197 • Published Aug 19 • 48