False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 158
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It Paper • 2609.36585 • Published Sep 29 • 29
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 179
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published Sep 15 • 286