MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling Paper • 2606.13473 • Published 24 days ago • 92
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation Paper • 2605.31264 • Published May 29 • 123
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? Paper • 2603.03194 • Published Mar 3 • 57