False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 12 days ago • 603
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 13 days ago • 553
view article Article autotrust/JEV-27B: fast, calibrated decisions and full reasoning from one open model autotrust • 15 days ago • 47