The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 9 days ago • 578
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 8 days ago • 673
Unlocking Lossless Speedups in LLMs via Discrete Diffusion Paper • 2609.04010 • Published Sep 3 • 115