SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments Paper • 2610.12611 • Published 30 days ago • 83
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 168
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published Sep 28 • 89