False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 4 days ago • 337
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 5 days ago • 419
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published 19 days ago • 815
Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement Paper • 2608.31046 • Published Aug 31 • 97