The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 8 days ago • 578
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents Paper • 2609.39982 • Published 7 days ago • 116
Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively? Paper • 2609.39578 • Published 7 days ago • 67