From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation Paper • 2610.06100 • Published 5 days ago • 122
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 10 days ago • 362
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 11 days ago • 397