SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments Paper • 2610.12611 • Published 12 days ago • 113
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 21 days ago • 565
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 20 days ago • 665
Transferring the Intelligence of VLMs to Robotic Control Paper • 2609.22966 • Published about 1 month ago • 94