The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 208
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 235
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction Paper • 2609.10715 • Published Sep 9 • 198