False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 9 days ago • 677
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 10 days ago • 582
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments Paper • 2609.04148 • Published Sep 3 • 249
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes Paper • 2609.03796 • Published Sep 3 • 186