From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation Paper • 2610.06100 • Published 24 days ago • 80
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published about 1 month ago • 208
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 29 days ago • 235
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments Paper • 2609.04148 • Published Sep 3 • 94