[2604.13010] Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation

Abstract:On-policy distillation (OPD) is an effective post-training paradigm for large language models but requires a live teacher server throughout training, resulting in substantial infrastructure overhead. We investigate whether OPD can be performed offline by precomputing teacher log-probabilities once over SFT rollouts and reusing them during training. We find that naively doing so fails to reliably match standard OPD, and trace the root cause to a previously overlooked condition we term teacher consistency, requiring that the same teacher be used for both supervised fine-tuning and OPD. Violating this condition introduces a gradient bias that degrades performance for both offline and online OPD. Building on this insight, we propose Lightning OPD, an offline on-policy distillation framework that enforces teacher consistency and eliminates the need for a live teacher server entirely. We prove that, under teacher consistency, Lightning OPD shares the same optimum as standard OPD, with bounded gradient discrepancy and an implicit regularization effect that helps prevent policy drift. Experiments on math reasoning and code generation show that Lightning OPD achieves comparable performance to standard OPD while delivering 4.0x higher training efficiency. Starting from an SFT-initialized Qwen3-8B-Base model, Lightning OPD reaches 69.9% on AIME 2024 in just 30 GPU hours. Lightning OPD further scales to MoE architectures, training Qwen3-30B-A3B to 71.0% on AIME 2024 on a single 8xH100 node, substantially lowering the barrier for academic research on LLM post-training. Our code is released at this https URL.

# link_1gvqmduzl9r.pdf ## Metadata - PDFFormatVersion=1.7 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - Author=Yecheng Wu; Song Han; Hai Cai - Creator=arXiv GenPDF (tex2pdf:a6404ea) - Custom.DOI=https://doi.org/10.48550/arXiv.2604.13010 - Custom.License=http://creativecommons.org/licenses/by/4.0/ - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.28 (TeX Live 2025) kpathsea version 6.4.1 - Custom.arXivID=https://arxiv.org/abs/2604.13010v2 - Producer=pikepdf 8.15.1 - Title=Lightning OPD: Efficient

saved by

• Christina Lee
• Sean Lee

related reading

• [2604.00626] A Survey of On-Policy Distillation for Large Language Modelsarxiv.org
• On-Policy Distillation - Thinking Machines Labthinkingmachines.ai
• [2605.23857] Strong Teacher Not Needed? On Distillation in LLM Pretrainingarxiv.org
• [2605.03327] DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignmentarxiv.org
• [2601.18734] Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Modelsarxiv.org
• SFT, RL, and On-Policy Distillation Through a Distributional Lens | whnrehiew.github.io
• Pedagogical RL: Teaching Models to Teach Themselves from Privileged Information - Noah Ziemsnoahziems.com
• LoRA Without Regret - Thinking Machines Labthinkingmachines.ai
• State of RL for reasoning LLMs | A. Weersaweers.de
• [2605.10889] Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Whyarxiv.org
• RLHF & Post-Training Course by Nathan Lambertrlhfbook.com
• ar0cket1 on X: "Solving OPSD (basically)" / Xx.com