On-Policy Distillation

Ask about this topic

Overview

On-policy distillation studies how to transfer a teacher’s capabilities by training a student on trajectories the student generates, rather than only on fixed teacher-written examples. Common approaches match teacher and student token distributions with KL-style objectives, often combining this dense feedback with verifier rewards, reinforcement learning, or feedback from successful peer attempts. Work spans language-model reasoning and tool-using agents as well as multimodal, speech, diffusion, and embodied models; methods increasingly select useful tokens, turns, or rollout lengths to reduce compute. A central tension is that student-generated states can make supervision more relevant, but teacher signals may be unreliable or mismatched, and repeated rollouts can be costly or destabilize training. 4 sentences total.

Latest papers

CardsList

511 papers178 papers in the last four weeks, up 141% on the four weeks before. 1.0% of all new papers.

Aug 7, 2026

MemOPD: On-Policy Distillation through Memory State Alignment for Long-Horizon Agents

Long-horizon agents accumulate growing contexts during interaction, impairing performance and stability. Compact memory mitigates this problem by compressing and rewriting the history retained between model invocations. Learning what to retain typically relies on proximal policy optimization (PPO) with final task rewards, but sparse rewards provide little guidance for individual memory updates. This limitation motivates on-policy distillation (OPD), which supplies dense teacher supervision on student rollouts. For such supervision to be valid, the teacher must evaluate each sampled action under the same state in which it was generated. However, the context rewriting performed during memory compression can break this alignment. When sampled responses are retained and re-encoded for later invocations, flattening the interaction into a persistent history may cause the teacher to score the action under a state that the student never visited during rollout. The action therefore remains on-policy by provenance, but not necessarily by state. We therefore propose Memory-Aligned On-Policy Distillation (MemOPD). MemOPD records the inputs and sampled outputs of each model invocation, restores its original token positions and causal visibility, and packs the reconstructed invocations for efficient teacher scoring. The teacher provides full-vocabulary supervision at the sampled action positions, while PPO preserves the final task objective. Experiments verify state alignment across several context updates and show that it improves F1 by 7.0% over persistent-history teacher scoring in a matched control. Overall, MemOPD-3B improves F1 over PPO by up to 416.2%, while packing yields up to a 1.63x speedup in actor computation during training. The code for this work is publicly available at: https://github.com/TPssp/MemOPD.

Zhiyuan Liu, Tinghong Ye, Chenghao Liu +2

School of Advanced Manufacturing and Robotics, Peking University · Zhejiang University · Harbin Institute of Technology

On-Policy DistillationMemory-Augmented AgentsRL for LLM Agents
AskPDF
Aug 7, 2026

FlowErase-OPD: Multi-Concept Erasure via Anchored On-Policy Distillation in Flow Matching Models

Recent advances in flow matching models have substantially improved the quality of text-to-image generation, but have also raised increasing safety concerns due to their potential to generate harmful or undesirable content. Existing concept erasure methods for flow matching models predominantly focus on removing individual concepts, while effectively erasing multiple concepts simultaneously remains challenging. We propose FlowErase-OPD, a framework for multi-concept erasure based on on-policy distillation (OPD). Our approach first distills multiple single-concept erased models into a unified LoRA module and introduces Anchored Multi-Teacher Distillation (AMTD), which incorporates a retention teacher to mitigate the trade-off between concept erasure and preservation of generative capabilities. To further improve the coordination of multiple erasure objectives, we develop Adaptive Retention Control (ARC), which dynamically adjusts the sampling frequency and loss weight of each erasure teacher, together with the relative contribution of erasure and retention teachers throughout training. Extensive experiments on nudity, object, and artistic-style erasure demonstrate that FlowErase-OPD consistently improves the trade-off between erasure effectiveness, image quality, and semantic alignment, achieving state-of-the-art performance across diverse multi-concept erasure settings. Furthermore, the resulting models exhibit strong robustness against adversarial attacks. These results highlight the potential of on-policy distillation as a principled framework for safe and controllable generation in flow matching models.

Yi Sun, Yimin Zhou, Xinhao Zhong +3

Harbin Institute of Technology, Shenzhen · Tsinghua Shenzhen International Graduate School, Tsinghua University · Peng Cheng Laboratory

Flow MatchingDiffusion Model UnlearningOn-Policy DistillationConcept Erasure
AskPDF
Aug 7, 2026

Simple-OPD: Demystifying Warm-up for On-policy Distillation

On-policy distillation (OPD) trains a student on its own rollouts with token-level supervision from teacher models, but its effectiveness can depend strongly on the warm-up stage before OPD. In this paper, we demystify warm-up for OPD from both data and training perspectives. For data, we find that effective warm-up relies on teacher-compatible chain-of-thought supervision, and that even incorrect teacher rollouts can provide comparable benefits to correct ones. This suggests that warm-up primarily transfers a teacher-compatible thinking pattern rather than merely correct answers. For training, we show that low-rank adaptation (LoRA) with a near-saturation training duration better balances in-domain adaptation and out-of-distribution generalization than full-parameter SFT. Based on these findings, we propose Simple-OPD, a plug-and-play initialization method that warms up the student on teacher-generated CoT with LoRA before OPD. Experiments across diverse settings demonstrate the effectiveness and robustness of Simple-OPD.

Tao Liu, Taiqiang Wu, Mao Zheng +5

1Tsinghua University · 2The University of Hong Kong · 3LLM Department, Tencent

CoT DistillationOn-Policy Distillation
AskPDF
Aug 6, 2026

DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outcome signals, but these signals are typically sparse and at the sequence-level. On-policy self-distillation (OPSD) mitigates this sparsity by querying a privileged teacher at student-visited prefixes and providing dense token-level distributional supervision. Although this dense supervision alleviates signal sparsity, we find that standard OPSD still underexploits the temporal structure of the rollout. It assigns every local divergence the same coefficient, regardless of its position or the divergence sequence in which it occurs. In on-policy autoregressive generation, the same divergence magnitude can follow different discrepancy histories, reflecting different evolutions of the mismatch between the teacher and student. Since the local scalar alone cannot distinguish these temporal contexts, standard OPSD cannot adapt its token-level weights to the realized discrepancy sequence. To address this limitation, we propose Divergence-Adaptive Supervision Horizons (DASH). DASH maps the gap between each local distillation signal and the sequence-level mean to an adaptive propagation gate and then uses these gates to control backward multi-step aggregation. By doing so, DASH adjusts token-level supervision weights according to how local divergences evolve during generation. Experiments on three mathematical reasoning benchmarks across three model scales show that DASH improves over our matched vanilla OPSD reruns on every benchmark at all three scales. DASH reuses the teacher and student distributions that OPSD already computes, so the gains require no additional teacher or student forward pass. Code: https://github.com/DBtxy/DASH-OPSD

ZhiYan Hou, Xinyu Tang, Hongyan An +9

Institute of Automation, Chinese Academy of Sciences · EverMind · Shanda Group +3

On-Policy Self-DistillationRL for Language Model ReasoningReinforcement Learning with Verifiable RewardsOn-Policy DistillationLLM Reasoning
AskPDF
Aug 6, 2026

On-Policy Delta Distillation for Multilingual Math Reasoning

On-Policy Distillation (OPD) is emerging as a promising alternative to reinforcement learning for LLM post-training, yet its effectiveness in multilingual settings remains underexplored. We study OPD and its advanced variant, On-Policy Delta Distillation (OPD2^2), for mathematical reasoning in English, Korean, and Japanese. OPD2^2 improves OPD by using the probability gap between a post-trained teacher and its base model as the learning signal. Experiments with Qwen3 show that OPD2^2 consistently outperforms the original OPD, with particularly strong improvements in Korean and Japanese, and generally narrows the English-Korean performance gap. We further find that English-only OPD can also increase performance for Korean and Japanese, but often shifts the responses toward English, highlighting the importance of multilingual data to preserving target-language responses.

Byeongho Heo, Jaehui Hwang, Sangdoo Yun +1

NAVER AI Lab

Numerical Reasoning in Language ModelsMultilingual Language ModelsCross-Lingual Reasoning in Language ModelsLanguage Model DistillationOn-Policy Distillation
AskPDF
Aug 5, 2026

STEP-OPD: Rethinking Output Targets and Internal Dynamics in On-Policy Distillation for Diffusion Models

On-policy distillation (OPD) has become an effective approach for consolidating multiple task-specialized image generation models into a single student. However, existing OPD methods optimize the student mainly to match the teacher's output velocity, making the teacher the upper limit of the optimization objective. While output-level supervision alone leaves the student's blockwise representation evolution underconstrained, which weakens the transfer of capabilities that must be progressively developed across layers. We propose STEP-OPD, an on-policy distillation framework for image generation that extends the student's learning target beyond the teacher and introduces explicit constraints on its internal representation evolution. Instead of treating the teacher as the final target, we use the velocity difference between each task-specific teacher and the shared base model as a direction for further learning and add a scaled version of this difference to the teacher velocity. In addition, we align the direction and magnitude of representation changes between the student and teacher, enabling the student to learn how representations are progressively transformed across network blocks. Experiments on compositional alignment, text rendering, and human preference show that our method consistently improves Standard OPD methods. In particular, it increases the GenEval score of DiffusionOPD from 0.927 to 0.961, while also improving OCR and all preference-based metrics. The resulting unified student surpasses the corresponding single-task teachers across all three capability groups, showing that output extrapolation enables beyond-teacher learning. And representation change alignment provides complementary guidance for the student's internal transformations.

Qingyan Wei, Guangzhao Li, Xiaobing Tu +5

Shanghai Jiao Tong University · Shanghai Innovation Institute · Alibaba Group

Diffusion Model DistillationDiffusion-Based Image GenerationOn-Policy Distillation
AskPDF
Aug 5, 2026

Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation

Large language model agents are commonly trained through reinforcement learning with sparse trajectory-level rewards, which offer limited guidance on how strongly individual tokens should be updated. On-Policy Self-Distillation (OPSD) addresses this by re-scoring generated tokens under a privileged replay view to obtain dense, token-level supervision. However, we identify a confounding issue: the resulting support may reflect both the privileged information contained in the replay view and score shifts induced by the replay scaffold, making it difficult to attribute the support specifically to that information. This issue is especially pronounced when future environment observations serve as privileged information, since replaying them requires reconstructing an extended scaffold that itself perturbs token scores. To resolve this confounding, we propose Observation-Calibrated Self-Distillation (OCSD), which contrasts two structurally matched replay views, Full and Observation-Ablated, differing only in whether the actual future observation is present, to derive an observation residual that discounts score changes shared by the replay scaffold. OCSD then applies this residual to modulate token-level GRPO updates at high-uncertainty steps, while preserving the trajectory-level update direction. Experiments on ALFWorld, WebShop, and Search-QA across three Qwen3 model scales show that OCSD consistently outperforms strong baselines. Diagnostic analyses further confirm that the calibrated residual aligns better with local environment feedback. Our code is publicly available at https://github.com/yiy1x/OCSD.

Yi Yang, Cong Qin, Xiaodan Liu +8

Meituan LongCat Interaction · Nanjing University · Peking University +3

Agentic RLOn-Policy DistillationRL Post-TrainingRL for LLM Agents
AskPDF
Aug 5, 2026

When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents

Multi-turn agents trained with sparse outcome rewards receive limited supervision for intermediate decisions. Privileged on-policy self-distillation provides denser guidance by having a synchronized teacher re-score student responses with training-only references. However, the student may take different actions or complete subgoals in another order, reaching states for which the reference provides no applicable continuation. The resulting state--reference mismatch can lead the reference-conditioned teacher to penalize valid actions. We introduce State-Matched Routing and Contextualized Self-Distillation (SMRC-SD), which uses the student's reached state to decide when and how a reference should guide the student. At each turn, SMRC-SD checks state compatibility with the reference, distills only on matched turns, and contextualizes the reference by augmenting it with a reached-state summary and a compatible continuation. At inference, the policy requires neither references nor state matching. Experiments spanning three model sizes show gains over unconditional full-path self-distillation in embodied interaction (ALFWorld), web navigation (WebShop), and tool use (FTRL). FTRL-trained policies also transfer to BFCL and ToolHop without additional training. Code is available at https://github.com/liujunzhuo/SMRC-SD.

Junzhuo Liu, Weiwei Li, Jun Ling +1

University of Electronic Science and Technology of China

Language Model DistillationOn-Policy DistillationKnowledge DistillationRL for LLM Agents
AskPDF
Aug 5, 2026

SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation

On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but standard reverse-KL training can assign insufficient probability to other plausible continuations. Teacher entropy alone does not reveal whether uncertainty is concentrated among a few plausible next tokens or dispersed over a long probability tail, nor whether the student already represents those candidates well. Moreover, local teacher probabilities may not predict downstream success. We introduce Sparse Probing and Outcome-calibrated Targets OPD (SPOT), which addresses two coupled decisions, where to probe and what to distill, through an acquisition--exploration--exploitation procedure. During acquisition, a position-level score combines normalized teacher entropy, the probability mass captured by a small top-kk candidate set, and student--teacher mismatch to allocate a limited probing budget. During exploration, SPOT evaluates teacher-proposed candidates through verifier-scored student continuations. During exploitation, these outcomes produce a closed-form, KL-regularized target that favors candidates with better downstream outcomes while remaining anchored to the teacher distribution. Extensive experiments across multiple student models and reasoning benchmarks demonstrate the effectiveness of SPOT in improving reasoning performance while balancing solution quality and coverage.

Zikun Qu, Min Zhang, Mingze Kong +4

The Chinese University of Hong Kong, Shenzhen · East China Normal University · Beihang University +1

Language Model DistillationOn-Policy DistillationKnowledge Distillation
AskPDF
Aug 5, 2026

Not Every Divergence Should Be Suppressed: Counterfactual Recoverability in On-Policy Distillation

On-policy distillation (OPD) supervises student-visited trajectories, yet divergence-based rules cannot determine whether an erroneous prefix remains correctable. We formulate this decision as counterfactual recoverability and replay each error state through budget-matched teacher-continuation and rollback branches. Based on their relative success, states are categorized as recoverable, irreversible-but-avoidable, or ambiguous, and these labels guide whether training retains, rolls back, or conventionally supervises the corresponding trajectory. On AIME branch diagnostics, the mean continuation-minus-rollback effect is 0.185 for recoverable states and -1.000 for irreversible-but-avoidable states, demonstrating opposite intervention preferences. A branch-derived recoverability proxy achieves an AUC of 1.000, substantially outperforming divergence alone at 0.392. Across frozen evaluations, recoverability-aware control achieves the strongest recorded performance, reaching 0.578 success on held-out AIME2025 compared with 0.517 for the best baseline. It also improves AIME2024-2025 average@32 from 0.2656 to 0.3125 and GPQA-Diamond average@32 from 0.2702 to 0.3070. Component ablations further show that retaining teacher-correctable prefixes provides the largest individual contribution. These findings establish recoverability as an outcome-grounded decision variable for selective supervision in OPD.

De Jiang, Zhengyang Zhang, Kehong Yuan +1

Language Model DistillationOn-Policy DistillationCounterfactual Learning
AskPDF
Aug 5, 2026

Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models

Leading open text-to-image models often carry complementary strengths: one may lead on preference-aligned aesthetics while another follows compositional instructions more faithfully. However, differences in their autoencoders and noise schedules make it difficult to transfer these strengths across models. In this paper, we present Poly-OPD, a framework that can consolidate complementary strengths of heterogeneous teachers into a single compact flow-matching student. To bridge the incompatible latent spaces of different teachers, Poly-OPD performs on-policy distillation through a pixel bridge. Each student-generated image is re-encoded by a selected teacher's encoder and refined from a noise level matched by magnitude under the teacher's noise schedule. The resulting target is further matched to the student in frozen DINOv2 space, enabling supervision across incompatible latent spaces. To retain complementary capabilities without cross-teacher interference, Poly-OPD uses a gradient compatibility diagnostic to organize its adapters: attention LoRA modules are shared across teachers, whereas feed-forward adapters remain teacher-specific. During distillation, a gap-aware curriculum devotes more training to compositional categories where the student still falls short of the teacher. As each gap narrows, training shifts toward categories with larger remaining gaps. By distilling FLUX.1-dev and Z-Image into a 2.5B SD3.5-Medium student, Poly-OPD improves GenEval from 67.3 to 73.3, surpassing both larger teachers, and raises DrawBench HPSv3 from 9.34 to 11.35, consolidating both strengths within a switchable model.

Siming Fu, Haojun Xu, Ruizhe He +9

1Joy Future Academy · 2Zhejiang University · 3Beihang University

Diffusion Model DistillationMulti-Teacher Knowledge DistillationOn-Policy DistillationT2I Diffusion Models
AskPDF
Aug 4, 2026

CausalOPD: First-Wrong-Step Supervision for Distilling Causal Chain Reasoning

Many critical reasoning tasks, including clinical diagnosis, legal judgment, and industrial fault diagnosis, require step-dependent causal chains in which early errors propagate and correct conclusions can mask invalid reasoning. Although large language models perform well on such tasks, privacy, latency, and controllability motivate distillation into locally deployable models. Standard trajectory imitation does not correct process errors on the student's own rollout distribution. We propose CausalOPD, a curriculum online process distillation framework. A knowledge-augmented teacher first provides trajectories grounded in domain-specific causal rules, entity relations, and structural constraints. The student then generates on-policy trajectories, and the teacher identifies the first wrong step, defined as the earliest transition that verifiably violates available constraints. Starting from the verified prefix, short-horizon reinforcement learning repairs this localized failure. A causal-stage curriculum advances from evidence-level to mechanism-level and conclusion-level errors, following their propagation order. Across three domains, CausalOPD improves average path correctness by 23.4 percentage points over sequence-level online process distillation and reduces the right-label-wrong-reasoning rate from 15.7% to 4.4%. The domain-specific 8B students also surpass both evaluated proprietary references in path correctness across all domains.

Jian Zhang, Bingyi Wang, Yizhi Liu

Zhejiang University

Curriculum RLCausal Reasoning in Language ModelsProcess SupervisionCausal ReasoningOn-Policy Distillation
AskPDF
Aug 4, 2026

When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation

On-Policy distillation (OPD) transfers teacher capabilities by supervising student-sampled trajectories with dense token-level teacher signals. Recent selective OPD methods improve this process by prioritizing signals that are confident, informative, or learnable. However, the assumptions overlook a fundamental failure mode of language models: their token-level judgments can be driven by input-agnostic language priors, formatting conventions, or stereotyped reasoning templates rather than task-specific evidence. We refer to such optimization-relevant but weakly input-grounded supervision as spurious signals in OPD, which may produce large gradients while contributing little task-improving direction. To mitigate this issue, we propose SA-OPD, a Spurious-Signal-Aware On-Policy Distillation framework that identifies and filters misleading token-level supervision based on input-groundedness and optimization impact. SA-OPD introduces a lightweight input-groundedness proxy estimating whether a token-level distillation signal truly depends on the input. It then filters only tokens that simultaneously exhibit low input-groundedness and extreme distillation divergence, thereby removing high-impact spurious updates and achieving fine-grained OPD optimization. Extensive experiments on both large language model (LLM) and vision-language model (VLM) settings demonstrate that SA-OPD consistently outperforms Vanilla OPD and competitive selective methods. These results establish input-groundedness as a key dimension for OPD supervision selection and offer a simple, effective strategy for mitigating spurious updates.

Yinuo Jiang, Yongjie Ye, Zhou Tao +4

Zhejiang University · ByteDance · Shanghai Artificial Intelligence Laboratory

VLM DistillationLanguage Model DistillationOn-Policy DistillationSelf-Supervised Knowledge DistillationKnowledge Distillation
AskPDF
Aug 4, 2026

Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR

Modern LLM-based ASR systems have established multilingual capability as a standard feature, leveraging large-scale multilingual corpora and LLMs' cross-lingual knowledge to achieve competitive performance across multilingual benchmarks. However, jointly modeling languages with heterogeneous acoustic, phonological, and lexical characteristics inevitably introduces optimization conflicts, undermining language-wise specialization. To address this challenge, we propose Language-Specialized Multi-Teacher On-Policy Distillation (LS-MOPD), which decouples language-specific knowledge acquisition from multilingual capability integration: language-specialized teachers are independently optimized via reinforcement learning (RL), with their expertise then integrated into a generalist multilingual student through language routing and token-level multi-teacher distillation, thereby reducing direct cross-lingual optimization conflicts. We further explore static and dynamic acoustic-prefix configurations to examine how teacher-student prefix consistency influences the efficacy of on-policy distillation. Experiments on benchmarks covering Mandarin, Mandarin subdialects, Cantonese, and English demonstrate that LS-MOPD substantially outperforms RL baselines and surpasses the empirical performance envelope defined by the best-performing RL teachers on nearly all benchmarks, revealing its potential to generalize beyond all teachers in multilingual ASR.

Yuan Xie, Jiaqi Song, Xianliang Wang +3

Advanced Intelligent Systems Group, NIO, Beijing, China

Multilingual Language ModelsMulti-Teacher Knowledge DistillationOn-Policy DistillationMultilingual ASR
AskPDF
Aug 4, 2026

Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging

On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, matching architectures, and a common timestep grid. We ask what happens when none of this holds, as when the strongest teacher available and the student one wishes to deploy come from different model families, and find that the standard recipes have no answer: teacher latents cannot serve as targets in a foreign coordinate system, per-pixel losses against a teacher that stochastically re-draws local detail degenerate into blur or divergence, and timestep indices lose their meaning across mismatched schedules. We present Any-OPD, to our knowledge the first framework for on-policy distillation between arbitrary pairs of latent flow-matching generators. Any-OPD treats the teacher purely as a black-box sampler and connects the two models at exactly one point: a frozen, model-agnostic vision representation in which their independently decoded outputs are compared, sidestepping every assumption about latents, features, or architecture. Trajectory correspondence is recovered by matching continuous noise levels instead of step indices, and a brief anchoring phase, in which teacher samples are re-encoded through the student's own VAE, ensures the on-policy gradient measures sample quality rather than domain mismatch. Distilling the 12B FLUX.1-dev into the 2.5B SD3.5-Medium, Any-OPD lifts the student's PickScore from 0.846 to 0.884 and HPSv3 from 9.12 to 10.97, rivaling the teacher at a fifth of its size, where direct latent regression fails to train at all.

Siming Fu, Zheming Fu, Ruizhe He +7

1Joy Future Academy · 2Zhejiang University

Flow MatchingDiffusion Model DistillationT2I GenerationCross-Architecture Knowledge DistillationOn-Policy Distillation
AskPDF
Aug 3, 2026

Rubrics as Privileged Information for Open-Ended Generation

On-policy self-distillation (OPSD), where a single model acts as both student and teacher with different contexts, has shown promise in verifiable domains like math, where hard privileged information (PI) in the form of ground-truth answers structurally constrains valid continuations. We extend OPSD to open-ended generation using soft PI in the form of rubrics that guide preferences but admit many valid responses. Rubrics have served as scalar rewards for reinforcement learning (RL); we show that they provide substantially richer signal as dense PI for distillation, and contrary to intuition, soft rubric PI provides a larger and more effective training signal on student roll-outs than hard reference completion PI in this regime. A reference completion is one point in a set of valid responses, so distilling towards it over-constrains the student, while rubrics specify the preference structure shared across the set of valid responses. We show the effectiveness of using rubrics as PI for open-ended generation across Qwen and Llama model families and show that it outperforms rubric-as-reward (RaR) RL using HealthBench, a benchmark that grades open-ended health responses against physician-created rubrics, providing dense token-level supervision for open-ended tasks; RuPI beats RaR RL by up to +0.10 absolute score and, under matched recipe and KL direction, beats reference-PI by +0.034 to +0.079 absolute score across three models. We further show that these findings generalize to training on the RubricHub Science corpus and evaluating on ResearchQA: soft rubric PI outperforms both reference-PI distillation and RaR RL (66.6% vs. 64.2% and 57.6%).

Deepika Bablani, Ajay Gupta, Wanming Chen

Apple

Open-Ended GenerationRubric-Based EvaluationOn-Policy DistillationRubric-Guided GenerationKnowledge DistillationText Generation
AskPDF
Aug 3, 2026

OPTD: On-Policy Transition Distillation with Consistency-Guided Adaptive Compression for Few-Step Diffusion Language Models

Diffusion language models (dLLMs) can predict many tokens in parallel, but accurate generation still requires many iterative denoising steps. Few-step distillation accelerates decoding by compressing multiple teacher steps into a single student transition. However, existing methods construct supervision on off-policy trajectories. At inference, the student's early parallel commitments alter the context of later predictions, so the states it actually visits drift away from the supervised ones--precisely when step compression is most aggressive. On-policy distillation is a natural remedy for this mismatch, but it leaves open how far each transition should advance: matching only the teacher's next action limits compression, while indiscriminately merging future actions can violate intermediate dependencies. To address this limitation, we propose OPTD, On-Policy Transition Distillation with consistency-guided adaptive compression. It samples partial states from the few-step student's own trajectories, uses a frozen, question-only teacher to identify outcome-aligned future candidates, and orders them by current-state confidence. The method then selects the longest prefix whose joint commitment preserves the teacher's rollout outcome. A set-bottleneck objective promotes every verified future candidate to the decoder's release threshold, while a frozen-teacher KL anchor regularizes all other active positions. Neither target construction nor training uses a gold response. Across four mathematical reasoning and code-generation benchmarks, OPTD consistently improves the quality--efficiency trade-off and attains the strongest overall quality-constrained AUP among the evaluated few-step baselines.

Xiaocheng Lu, Hualei Zhang, Shuhan Guo +8

HKUST · NWPU · PolyU

Diffusion Model DistillationDiffusion Language Model DecodingOn-Policy DistillationDiffusion Language Model Distillation
AskPDF
Aug 3, 2026

Cross-Domain Hybrid OPD for Generalizable Search Agents

Recent advances in Reinforcement Learning (RL) have substantially improved the capabilities of autonomous search agents, enabling sophisticated planning, and iterative retrieval over dynamic information sources. However, optimizing language models for specialized search behaviors often incurs an alignment tax, where gains in search performance come at the expense of general-purpose capabilities, limiting their effectiveness as universal assistants. In this technical report, we present the training framework behind the Yuanbao search agent, designed to achieve search specialization without sacrificing general intelligence. Built upon the Hunyuan3 architecture, our framework combines agentic reinforcement learning for autonomous search with a cross-domain expert On-Policy Distillation (OPD) pipeline. Experts specializing in complementary general-purpose domains are distilled into the search-specialized student, restoring and further enhancing its broad capabilities. Rather than treating specialization and general capability as competing objectives, our hybrid training strategy jointly optimizes both, effectively mitigating the alignment tax. Extensive experiments demonstrate that the resulting model achieves competitive search performance while consistently improving its general-purpose capabilities, providing a favorable balance between specialized execution and broad generalization in real-world search scenarios.

Hongzhan Chen, Xiaoyu Liu, Dengming Zhang +11

Yuanbao Team, Tencent · Shanghai Innovation Institute

Cross-Domain GeneralizationOn-Policy Distillation
AskPDF
Aug 3, 2026

Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation

On-policy distillation (OPD) provides teacher supervision on states visited by the student, reducing the distribution gap between training and inference. However, in multi-turn agentic tasks, student deviations may accumulate over time, gradually moving the trajectory away from states where teacher guidance remains effective. Our quantitative analysis further shows that high-disagreement states offer promising opportunities for teacher guidance, but determining whether such guidance is beneficial requires examining its effect on subsequent student trajectories. We propose FutureBridge-OPD (FTB), which executes a short teacher bridge at a high disagreement state and uses the resulting student continuation to assess whether the bridge increases the density of positive distillation signals relative to the teacher. On ALFWorld, WebShop, and ScienceWorld, under the main Qwen3-32B teacher to Qwen3-1.7B student setting, FTB outperforms vanilla OPD and TCOD by an average of 16.6 and 7.6 points, respectively, and remains effective across student scales and teacher settings. Our code is publicly available at https://github.com/ChenChiShui/FutureBridge-OPD.

Chishui Chen, Yaoyou Fan, Te Sun +11

Meituan LongCat Interaction · Peking University · Shanghai Jiao Tong University +6

LLM Agent TrainingOn-Policy DistillationKnowledge DistillationRL for LLM Agents
AskPDF
Aug 3, 2026

PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning

Large language model agents have shown strong potential in complex interactive tasks, yet their reinforcement learning (RL) is often hindered by sparse rewards, as a long multi-turn trajectory may receive only a single outcome-level signal. On-policy self-distillation (OPSD) provides dense token-level supervision from a privileged teacher, but the teacher may not be reliable at every position. Existing methods commonly rely on isolated token-level discrepancies, which can be sensitive to noise, or assign a shared step-level weight that may overlook positional variation. We propose Persistent Consistency Self-Distillation (PCSD), which derives token-level distillation weights from the local persistence of teacher-favoring signals. PCSD combines adaptive windows with exponentially decayed aggregation to capture persistent relative teacher support, applies trend-aware modulation to attenuate locally declining support, and produces continuous weights through sigmoid gating. The resulting objective is jointly optimized with GRPO, combining dense teacher guidance with sparse environmental feedback. Without inference-time skills, PCSD achieves the best ALFWorld Overall results among all baselines on both backbones, exceeding GRPO by 15.6 and 13.3 points and SDAR by 6.2 and 5.5 points, while remaining competitive on WebShop and gaining 15.8 points over GRPO on unseen ALFWorld split.

Chunji Lv, Yangguang Wei, Junlin Liu +6

Beijing Institute of Technology · Meituan · Institute of Automation, Chinese Academy of Sciences +1

Language Model DistillationOn-Policy DistillationSparse-Reward RLRL for LLM Agents
AskPDF
Aug 2, 2026

AlphaG-OPD: Reliability-Gated Sibling Counterfactuals for On-Policy Distillation in Symbolic Alpha Factor Discovery

Symbolic alpha factor discovery can score a completed expression, but it provides no direct label for the structural decisions that produced it. Generative flow networks (GFlowNets) preserve a diverse, reward-proportional distribution over complete expressions, yet their trajectory-level objective does not compare unchosen sibling actions at an intermediate state. We introduce AlphaG-OPD, a structural on-policy distillation framework that turns terminal factor evaluations into local action guidance. Its design separates three decisions. Component I determines where to teach by exposing grammar-valid siblings at partial abstract-syntax-tree (AST) states visited by the current forward policy. Component II determines what is reliable enough to teach: it evaluates three supported siblings under four shared suffixes and admits a KL-bounded target only when their matched comparisons exhibit sufficient winner agreement and a positive empirical lower confidence bound (LCB). Component III determines how strongly and for how long to teach by consolidating accepted targets through bounded replay, score-indexed expiry, and forward-gradient balancing, without additional factor evaluations. Terminal reward, Trajectory Balance, the backward policy, grammar, and factor-pool rules remain unchanged. An equal-physical-score four-arm ablation tests paired teaching, reliability gating, and consolidation. Across China's CSI300, CSI500, and CSI1000 and the U.S. S&P 500, the complete method delivers strong cross-market performance over multiple random seeds.

Yaoyu Su

Quantitative FinanceGenerative Flow NetworksOn-Policy DistillationCounterfactual LearningFinance
AskPDF
Aug 2, 2026

Distill What the Student Can See: Fisher-Projected On-Policy Distillation for Vision-Language Models

On-policy distillation (OPD) samples trajectories from the current student policy and minimizes token-level divergence between student and teacher next-token distributions at prefixes along those trajectories. This aligns the distillation states with the student's own generation distribution. However, it still assumes that the complete teacher distribution is an appropriate target across student capacities. In vision--language reasoning, teacher corrections can depend on visual distinctions that a compact student cannot represent. Our target-scaling study shows that, as the target approaches the complete teacher distribution, the student realizes less of the prescribed shift and obtains worse downstream performance. We therefore propose Fisher-Projected On-Policy Distillation (FP-OPD), which distills only locally realizable teacher corrections. FP-OPD uses continuous visual perturbations to estimate the student's local visual tangent space and projects the centered teacher--student log-probability gap onto this space under the student's Fisher metric. The resulting capacity-aware target is optimized with full-vocabulary reverse KL on student trajectories, retaining the standard OPD framework. In 8B-to-2B distillation, FP-OPD improves all seven evaluated multimodal benchmarks. It raises the average score by 2.77 points over the pretrained student and by 1.60 points over standard OPD. These results demonstrate that locally realizable teacher corrections provide a more effective target for distilling compact vision--language models.

Leyan Xue, Feng Xiong, Mingjun Ma +1

College of Intelligence and Computing Tianjin University Tianjin, China

VLM DistillationOn-Policy DistillationKnowledge Distillation
AskPDF
Aug 1, 2026

Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models (LLMs). While Group Relative Policy Optimization (GRPO) is widely adopted, it suffers from sparse reward signals and loses gradients entirely when all responses within a group receive identical rewards. On-policy distillation (OPD) offers a natural remedy by providing dense, token-level supervision from a teacher model. However, naively combining GRPO with OPD leads to degraded performance, due to three underlying causes: not all samples benefit from distillation; fitting too quickly to the teacher undermines the exploratory capacity of RL; and OPD's advantages are asymmetric, suppressing most tokens. To address these challenges, we propose RSTG (Recovering Learning Signals via Adaptive Teacher Guidance), which applies distillation selectively and precisely where it matters most. At the sample level, OPD is restricted to negative zero-variance prompts with each sample weighted by the teacher's confidence score. At the token level, distillation targets only tokens with high student entropy or large teacher-student divergence. We further augment training with SFT on correct trajectories generated by the teacher model, injecting positive gradient signals where RL yields none. Experiments demonstrate that RSTG substantially outperforms naive GRPO+OPD by +4.02% on math and +3.05% on code.

Zhuowen Han, Jinwei Xiao, Zhengxi Lu +9

TJUNLP Lab, School of Computer Science and Technology, Tianjin University · Meituan Longcat Team

Self-Training for Language ModelsRL for Language Model ReasoningSelective Knowledge DistillationReinforcement Learning with Verifiable RewardsOn-Policy DistillationKnowledge Distillation
AskPDF
Jul 31, 2026

Adaptive FastOPD: Progress-Aware Rollout Horizon Expansion for Efficient On-Policy Distillation

On-policy distillation (OPD) provides dense teacher supervision along student-generated trajectories, but its online rollout process incurs substantial computational cost, particularly when a few long responses delay batch completion. Existing acceleration methods typically control rollout length using fixed budgets or absolute teacher--student agreement thresholds, which may not reflect learning progress across different models and training stages. We propose Adaptive FastOPD, a progress-aware strategy that expands the rollout horizon only when learning near the current boundary region has plateaued and the current horizon is sufficiently utilized. The former is determined from four teacher--student signals measured relative to their values upon entering each horizon, making expansion responsive to stage-specific progress rather than a predefined step interval or an absolute threshold on the raw agreement signals, while the latter prevents a small number of long responses from triggering increases in rollout cost. Across two teacher--student pairs, Adaptive FastOPD achieves the highest average performance while reducing training time by 49.1--71.2% relative to OPD 15K, and remains robust across a range of hyperparameter settings.

Qian Tan, Huaifei Liang, Xuanyu Zhu +2

University of Science and Technology of China · 3Shanghai Jiao Tong University · 2Shanghai Artificial Intelligence Laboratory

Language Model DistillationOn-Policy Distillation
AskPDF
Jul 31, 2026

SAF-OPD: Stable Advantage Fusion for On-Policy Distillation

Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) scores each token against a stronger teacher for a dense advantage but caps performance at teacher quality and discourages exploration beyond it. Their complementarity makes combining RLVR and OPD promising, but we find that fusing the two advantages with a fixed coefficient triggers entropy collapse from two miscalibrations: a magnitude mismatch, where token-level OPD advantages can spike far beyond the bounded RLVR advantage and erase its signal, and a temporal mismatch, where sustained full-strength OPD keeps pulling the student toward the teacher and limits exploration needed to surpass it. We propose SAF, a Stable Advantage Fusion framework that resolves both issues via a lightweight, four-stage pipeline applied only to the OPD advantage: a sparsify-then-compress mechanism for magnitude control paired with a warm-up-then-anneal mechanism for temporal control, with each stage independently switchable and adding negligible overhead. Instantiating RLVR with GRPO, we evaluate SAF across seven mathematical reasoning and code generation benchmarks with Qwen3-1.7B/4B/8B: SAF avoids entropy collapse and consistently outperforms fixed-coefficient GRPO+OPD fusion, improving the aggregate score by 0.51-2.70% across all six model-domain settings while achieving more stable training.

Yifan Ding, Xincheng Wei, Yoshua Y. Li +7

Shanghai University of Finance and Economics · Meituan, LongCat Team · The Chinese University of Hong Kong, Shenzhen +1

RL for Language Model ReasoningReinforcement Learning with Verifiable RewardsOn-Policy Distillation
AskPDF
Jul 31, 2026

DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation

While on-policy distillation (OPD) reduces exposure bias by training student language models on their own rollouts, early student errors in long-horizon agentic scenarios can lead to contexts unfamiliar to the teacher. To improve trajectory quality, recent work on agentic OPD introduces teacher intervention into training rollouts by switching the executor between the student and the teacher. However, existing methods determine how much teacher intervention is needed---but not when. To address this limitation, we propose DASH-OPD (Discrepancy-Aware Switching with Hysteresis for OPD), the first agentic OPD method to perform adaptive, bidirectional executor switching. At each turn, DASH-OPD measures teacher--student discrepancy using a mean log-probability ratio over action tokens. Student-to-teacher ratios on student turns serve as drift signals, while teacher-to-student ratios on teacher turns serve as recovery signals. These signals are accumulated over multiple turns to form drift and recovery evidence, respectively. DASH-OPD switches executors when either type of evidence exceeds its corresponding switching threshold, introducing hysteresis that prevents rapid switching triggered by transient discrepancy fluctuations. Across three benchmarks and two student model sizes, DASH-OPD outperforms five baselines in all 14 task performance comparisons, while requiring the fewest interaction turns in nine of ten efficiency comparisons. Code, models, and training logs are available at https://github.com/Lucian1115/DASH-OPD

Yuchen Xia, Qianguo Sun, Chao Song +3

The Chinese University of Hong Kong · IDEA Research · Emdoor Research Institute

On-Policy DistillationTeacher-Student LearningKnowledge Distillation
AskPDF
Jul 30, 2026

VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation

Multimodal on-policy distillation (OPD) transfers fine-grained visual knowledge by supervising student-generated trajectories with a privileged-view teacher. Yet its next-token corrections are source-mixed, combining visual signals with linguistic priors and teacher-specific effects. The key challenge is to estimate which corrections are supported by visual evidence, not merely where or how strongly to distill. We introduce Visual Attribution Distillation (VAD), a counterfactual target-reconstruction algorithm that estimates the visually attributable part of a teacher correction. At each student-generated prefix, VAD evaluates the same fixed teacher with the relevant evidence present and removed. The corresponding change in centered log-probabilities defines ut, a signed proxy for the visual evidence direction that estimates how revealing the evidence supports or refutes candidate tokens. VAD projects the original correction onto this proxy to obtain an intervention-aligned component and a proxy-unexplained residual, then reconstructs a student-anchored target from the former. During training, this reconstructed target supplies the primary supervision signal, while the privileged teacher contributes a weak regularizer. Across six fine-grained visual benchmarks at 4B and 9B scales, VAD outperforms direct privileged-view distillation and visual-advantage weighting. Token- level and controlled-target analyses show that the proxy-aligned component is enriched in task-relevant visual corrections and yields stronger target shifts, especially when evidence refutes a mistaken answer. These results support counterfactual target reconstruction as an effective alternative to source-mixed supervision.

Kangning Zhang, Yixing Li, Shuai Shao +9

Shanghai Jiao Tong University · Xiaohongshu Inc. · The Chinese University of Hong Kong +1

Feature AttributionVLM DistillationOn-Policy Distillation
AskPDF
Jul 30, 2026

Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models

On-policy distillation (OPD) provides dense token-level supervision from a teacher, but its effectiveness can depend on teacher consistency, meaning that the model providing OPD supervision should also have generated the demonstrations used to train the supervised fine-tuning (SFT) reference. However, this condition is frequently violated in practice when SFT data have mixed or unknown provenance or when different models are preferred for SFT data generation and subsequent distillation. In such cross-teacher settings, even a stronger OPD teacher can yield little improvement over the SFT reference. We find that raw teacher--reference disagreement contains potentially useful context-specific teacher evidence as well as a recurring component associated with differences in wording, formatting, and reasoning cadence. We introduce Lightning OPD 2.0 with cross-fitted style residualization, which uses rollout-level cross-fitting to estimate this recurring component as an operational proxy for style-token bias and subtracts it before constructing the token-level OPD update. Across mathematical reasoning and code generation benchmarks, Lightning OPD 2.0 consistently outperforms Lightning OPD in cross-teacher settings. Starting from Klear-Reasoner-8B-SFT, Lightning OPD 2.0 reaches 82.4% on AIME 2024 and 63.0% on LiveCodeBench v5. Together, these results establish Lightning OPD 2.0 as a practical approach to cross-teacher OPD, relaxing teacher consistency as a prerequisite and allowing the SFT data generator and distillation teacher to be selected independently. Code will be released soon.

Yecheng Wu, Song Han, Han Cai

NVIDIA

Language Model DistillationOn-Policy DistillationKnowledge DistillationLLM Reasoning
AskPDF
Jul 30, 2026

Correcting What You Cannot See: Credit Assignment for Perception Distillation in Multimodal Reasoners

On-policy distillation provides dense supervision for multimodal reasoners, but its trajectory-level reward cannot determine whether a failed answer arose from perception or subsequent reasoning. Perception Success Rate (PSR), estimated from multiple reasonings sharing one perception, remains ambiguous because low success conflates perceptual insufficiency with reasoning difficulty. We introduce Perception-Correction Distillation (PCD), a label-free method that identifies correctable perception failures using downstream failure and teacher--student disagreement as complementary witnesses. Their product, , forms a soft AND gate that strengthens distillation only when both witnesses are present. We motivate this rule through Bayesian evidence combination and show that multiplication is the unique normalized bilinear gate that vanishes when either witness is absent. PCD uses separated perception--reasoning rollouts and mean-preserving weights, leaving the reasoning objective unchanged. Across eight benchmarks, PCD improves the 8B 2B macro average from 44.50 with OPD to 47.28 and the 32B 8B result from 56.94 to 61.22. In matched 2B ablations, removing PCD and separated rollout reduces held-out average by 2.22 and 0.88 points, respectively. Effective multimodal distillation therefore depends not only on what the teacher predicts, but also on identifying when perception is the appropriate target of correction.

Feng Xiong, Leyan Xue, Hongyu Lin

DeepSeek-AI

Multimodal ReasoningOn-Policy Distillation
AskPDF
Jul 30, 2026

OPLD: On-Policy Latent Distillation for Multimodal Reasoning

Interleaved multimodal Chain-of-Thought (CoT) improves visual reasoning by incorporating auxiliary visual evidence into intermediate reasoning. However, existing approaches remain constrained by externally defined reasoning traces and visual operations, limiting their ability to develop flexible and abstract visual thinking. Reasoning with latent has recently offered a promising direction by internalizing intermediate computation into continuous representations. Nevertheless, existing visual-latent methods mainly supervise latent states through alignment with compressed auxiliary visual features, treating them as proxies for visual observations rather than active reasoning states. Consequently, they capture the provided evidence but fail to fully internalize the abstract reasoning process induced by multimodal CoT. In this paper, we propose OPLD (On-Policy Latent Distillation), a simple framework that transfers the reasoning capability induced by privileged multimodal CoT into latent reasoning representations. Extensive experiments on diverse multimodal benchmarks demonstrate that OPLD consistently outperforms existing latent reasoning methods and achieves state-of-the-art performance on multiple benchmarks. The results suggest that supervising latent representations at the reasoning-process level provides a more effective paradigm for multimodal latent reasoning than conventional feature-level alignment.

Shoutai Zhu, Tianyang Xu, Bin Sun +3

ByteDance

Multimodal ReasoningLatent Visual ReasoningMultimodal CoT ReasoningOn-Policy Distillation
AskPDF