False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 7 days ago • 672
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 8 days ago • 578
Does Learning Protein Folding Generalize to Broader Reasoning? Paper • 2609.38879 • Published 7 days ago • 121
Transferring the Intelligence of VLMs to Robotic Control Paper • 2609.22966 • Published 18 days ago • 120
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments Paper • 2609.04148 • Published Sep 3 • 248