WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution Paper • 2610.18067 • Published 22 days ago • 35
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 168
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 151