ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement Paper • 2609.14857 • Published 23 days ago • 215
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement Paper • 2609.14857 • Published 23 days ago • 215
WebWorld: The Browser as a World Model for Self-Improving Web Code Paper • 2608.30530 • Published Aug 31 • 10
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild Paper • 2608.23181 • Published Aug 24 • 34
Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models Paper • 2608.16647 • Published Aug 17 • 16