LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets Paper • 2610.09872 • Published 24 days ago • 62
LeWAM: End-to-End World and Action Modeling with JEPAs Paper • 2610.12818 • Published 23 days ago • 33
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 208
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published about 1 month ago • 235
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published Sep 15 • 318