The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 5 days ago • 465
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 4 days ago • 392
PaperGym: Rubric-Centered Evolution for Research-Plan Generation Paper • 2608.31119 • Published Aug 31 • 33