The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 4 days ago • 418
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 3 days ago • 336
Realtime-Venus: A full-duplex interaction system with asynchronous delegation Paper • 2609.13814 • Published 21 days ago • 225