False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 14 days ago • 662
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 15 days ago • 561
Does Learning Protein Folding Generalize to Broader Reasoning? Paper • 2609.38879 • Published 14 days ago • 63
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions Paper • 2609.04199 • Published Sep 3 • 332