The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 20 days ago • 565
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States Paper • 2610.01415 • Published 18 days ago • 93
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning Paper • 2608.26105 • Published Aug 26 • 152