Capable Teacher, Myopic Scorer: Reward-Free Teacher Repair for Agentic On-Policy Distillation

arXiv:2610.28586 · cs.CL, cs.AI · Submitted 2026-10-20 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-10-20

Updated: 2026-10-20

Terminology

Related papers