Paper recorded by Signals 4 on 2026-10-14 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-14 on arXiv · recorded by Signals 4 on 2026-10-15
Category: cs.AI · 人工智能 · first seen 2026-10-15
On-policy self-distillation provides dense supervision for reasoning models via a privileged self-teacher. However, this supervision reflects local token preferences rather than the expected return of an unguided student continuation. Recent methods combine this signal with GRPO. They use GRPO for update directions and the teacher for signal scaling. However, we demonstrate a more effective integr