HINT-WAM: Hindsight-Informed Training for World Action Models Paper • 2611.24789 • Published 1 day ago • 23
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 130
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 146
view article Article autotrust/JEV-27B: fast, calibrated decisions and full reasoning from one open model autotrust • Sep 27 • 23
SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation Paper • 2608.18565 • Published Aug 19 • 20