X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning Paper • 2610.16811 • Published Oct 12 • 27
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 146
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It Paper • 2609.36585 • Published Sep 29 • 26
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 130
WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation Paper • 2609.30221 • Published Sep 24 • 39