False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 2 days ago • 181
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 3 days ago • 270
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models Paper • 2609.02886 • Published 30 days ago • 118