Skip to content

On the Off-Policy Teacher in On-Policy Distillation

Sep 2026 · arXiv.org · Vol abs/2609.38360 · 1 citation · 30 references
Computer Science

TL;DR

Control experiments show that SCOUT improves the teacher's ability to continue from student-generated prefixes, supporting the intended mechanism of student-conditioned teacher adaptation, and consistently improves the effectiveness of on-policy distillation.

Abstract

On-policy distillation (OPD) has recently emerged as a promising post-training paradigm in which the student learns from trajectories generated by its own policy under dense teacher supervision. However, OPD introduces a fundamental asymmetry: although the sampled trajectories are on-policy for the student, they are off-policy for the teacher. The teacher is typically optimized to continue from prefixes generated by its own policy, but during OPD it must instead supervise prefixes generated by the student. Empirically, we find that its continuation performance degrades as these prefixes grow longer. To address this issue, we propose Student-COnditioned Updates of the Teacher (SCOUT), a co-training framework that adapts the teacher to student-generated prefixes. Alongside standard OPD updates, SCOUT periodically optimizes the teacher's conditional ability using reinforcement learning with verifiable rewards, where the teacher generates continuations from student prefixes and learns from outcome rewards. Controlled experiments show that SCOUT improves the teacher's ability to continue from student-generated prefixes, supporting the intended mechanism of student-conditioned teacher adaptation. Across multiple teacher--student configurations, model scales, and reasoning domains, SCOUT also consistently improves the effectiveness of on-policy distillation.

View source

Similar papers

#machine learning Preprint Oct 2026

On-Policy Distillation with Negative-Policy Rollouts

On-policy distillation (OPD) has been widely studied as a post-training method in which a student model obtains token-level supervision from a stronger teacher on its own rollouts. Recent studies have improved OPD through alternative distillation reward formulations and teacher configurations, while the objective of di...

Jaehui Hwang, Dongyoon Han, Sangdoo Yun et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Teacher Should Think Ahead: Adaptive Continuations for Reliable On-Policy Distillation

This work identifies Teacher Uncertainty Contraction (TUC), a systematic phenomenon whereby the teacher's predictive uncertainty decreases as it continues from a student-generated prefix, and proposes Adaptive-Continuations On-Policy Distillation (AC-OPD), which augments informative states along student rollouts with t...

Jin-Gang Zhou, Yu-Yi Zhou, Hai-Yang Guo et al. · 3 citations
#artificial intelligence Preprint Oct 2026

A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching

Reinforcement Learning (RL) from outcome rewards suffers from sparse supervision, particularly on difficult, long-horizon tasks where successful trajectories are rare and costly to generate. On-Policy Distillation (OPD) offers an attractive alternative by providing dense token-level supervision from a stronger teacher...

Randy Ardywibowo, Arnav Dalal, Jian-Tao Jiao · 1 citation
#machine learning Preprint Oct 2026

Learning from Evolving Errors: Adaptive Iterative Repair for On-Policy Distillation

On-policy self-distillation (OPSD) supplies dense token-level feedback on trajectories sampled from the student's own policy, a richer training signal than the outcome-level rewards of reinforcement learning. This feedback comes from a teacher conditioned on a full reference solution unavailable to the student. The ref...

Rui Li, Li-Yang He, Zheng Zhang et al. · 0 citations

Recursive Self-Improvement via On-Policy Distillation for Reasoning

DCE+SRCL outperforms OPSD across multiple model scales and four competition-level mathematics benchmarks, and its comprehensive evaluations show that DCE+SRCL outperforms OPSD across multiple model scales and four competition-level mathematics benchmarks.

Shang-Jian Yin, Ze-Hao Zhao, Kavosh Asadi et al. · 6 citations

Reward-Aligned Reweighting for On-Policy Distillation

Reward-Aligned Reweighting for On-Policy Distillation (R$^{2}$-OPD), which uses outcome agreement and the magnitude of teacher--student disagreement to continuously reallocate teacher supervision, achieves the highest average accuracy among the compared training methods in both cross-size and same-size distillation.

Hao Xu, Junwei Su, Lan-Song Diao et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Sep 29, 2026

Who we become when we talk to machines

Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.