← Back to all news
arXiv Computation and Language By Yang Li, Gongle Xue, Yuheng Yuan, Yijia Guo, Shizhe Zhang, Liwen Hu, Lei Ma

Diagnosing On-Policy Self-Distillation for Reasoning Language Models

Read the original on arXiv Computation and Language →

The paper investigates on‑policy self‑distillation (OPSD) as a method to enhance reasoning in language models, focusing on mathematical reasoning across models from 0.6B to 8B parameters. Through controlled experiments and token‑level analysis, the authors find that OPSD’s effectiveness depends on alignment between the teacher’s reasoning mode and the full teacher prefix, rather than on privileged semantics alone. They observe that OPSD only improves reasoning in limited compatibility regimes, while often causing length growth, degradation, or behavioral collapse, and that the teacher’s signal is unstable and not predictive of downstream performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Machine Learning
4d ago

Teach Yourself Where to Look: On-Policy Attention Self-Distillation for Reasoning

The paper introduces On-Policy Attention Self-Distillation (OPASD), a method that augments token-level supervision with solution-conditioned attention distillation for reasoning models. OPASD projects a privileged teacher’s attention onto student-visible positions, renormalizes the distribution, and aligns it with the student. Experiments on three model sizes and four math benchmarks show that OPASD improves accuracy by 4.98–8.40 percentage points, reduces generated tokens by 73.9%, cuts compute by 72.6%, and trains 1.53× faster compared to token-only distillation.

By Safaeid Hossain Arib, Rabeya Akter, Ismam Nur Swapnil, Md. Faiyaz Abdullah Sayeedi, Tasnim Mohiuddin, Md Mofijul Islam
efficiencybenchmarkssafety
More like this →
arXiv AI
Aug 19

SOD: Step-wise On-policy Distillation for Small Language Model Agents

SOD: Step-wise On-policy Distillation for Small Language Model Agents proposes a new framework that adaptively reweights distillation strength at each reasoning step based on step-level divergence. This approach mitigates cascading errors in tool-integrated reasoning by attenuating misleading teacher signals in high-divergence regions while preserving dense guidance where student and teacher align. Experiments on math, science, and code benchmarks show up to 20.86% improvement over the second-best baseline, with a 0.6B student scoring 26.13% on AIME 2025.

By Qiyong Zhong, Mao Zheng, Mingyang Song, Xin Lin, Jie Sun, Houcheng Jiang, Xiang Wang, Junfeng Fang
llmsagentsreinforcement-learningefficiencybenchmarks
More like this →