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.

Jul 13, 2026

EasyOPD: An Easy-to-use On-Policy Distillation Framework for Large Language Models

Conventional language-model distillation often relies on fixed teacher-generated data, which may not cover the states encountered by an evolving student policy. On-policy distillation (OPD) instead collects teacher or evaluator supervision on student-generated rollouts. However, existing OPD methods differ substantially in supervision form, tokenizer compatibility, teacher access, and supervision granularity, leading to fragmented implementations that are difficult to reproduce and extend. We present EasyOPD, an on-policy distillation framework built on verl, a distributed reinforcement-learning framework for large language models. EasyOPD separates user-side configuration, method-specific supervision logic, and verl-based execution. Its method modules connect to the shared backend through extension boundaries for loss construction, rollout metadata, reward processing, tokenizer alignment, and teacher-side computation. We instantiate representative methods for three OPD settings -- cross-tokenizer OPD, on-policy self-distillation, and step-wise OPD. Experiments on reasoning, code-generation, scientific-knowledge, and tool-use benchmarks show that these implementations can be executed through the same verl-based backend while retaining their method-specific objectives and task-dependent performance profiles. We release EasyOPD with runnable YAML configurations, documentation, and an installable demonstration package and video.

Jie Sun, Mao Zheng, Mingyang Song +7

University of Science and Technology of China · Shanghai Innovation Institute · LLM Department, Tencent +1

Cross-Tokenizer Knowledge DistillationLanguage Model DistillationOn-Policy DistillationKnowledge Distillation
AskPDF
Jul 10, 2026

Mach-Mind-4-Flash Technical Report

We present Mach-Mind-4-Flash, a 35B-parameter Mixture-of-Experts (MoE) agentic model with 3B activated parameters. Through post-training optimization alone without scaling pre-training compute, the model achieves performance on par with or surpassing that of 100B-parameter-class models. By introducing scalable agentic interaction environments for large-scale reinforcement learning, the model attains significant performance gains on real-world application tasks. Our pipeline comprises three stages: (1) a unified RL/OPD training infrastructure with dynamic multi-teacher scheduling and operator-level acceleration, delivering 17% end-to-end training speedup; (2) multiple domain-specific RL experts trained in parallel across Reasoning, General, and Agent tracks, then fused into a single generalist via Multi-Teacher On-Policy Distillation (MOPD) -- a routed reverse-KL objective that eliminates the see-saw degradation of mixed-reward RL; (3) Hybrid Median-length Policy Optimization (HMPO), a single-stage token-efficiency method that compresses reasoning chains by 19--46% with ≤\le0.7 percentage-point accuracy loss. Mach-Mind-4-Flash scores 92.70 on AIME'26, 82.82 on IFBench, 80.74 on Behavioral-SafetyBench, 75.80 on BFCL-v4, 72.31 on BrowseComp-zh, and 84.20 on ClawBench -- leading or matching models with 10--30×\times its activated size at a fraction of the inference cost.

Foundation Model Team

Foundation Model, Li Auto Inc.

Agentic RLToken EfficiencyLLM Agent TrainingOn-Policy DistillationRL Post-TrainingMixture-of-Experts Models
AskPDF
Jul 8, 2026

Diagnosing and Calibrating Tool-Call Boundary Drift in Multi-Teacher On-Policy Distillation

Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly. This makes multi-teacher on-policy distillation a natural training strategy: one teacher can specialize in tool calls, another in direct responses, and the student can learn from both on its own generated distribution. We show that this strategy can induce a behavior shift that is invisible from aggregate losses alone. In a two-teacher tool-use setting, vanilla generalized knowledge distillation improves tool-call recall but also moves the model toward over-calling, where it calls tools on examples that should be answered directly. Aggregate explanations are insufficient: tool-call samples do not receive more token exposure, and full-sequence per-token divergence is not larger for the tool-call teacher. We instead analyze behavior leverage imbalance: local token-level signals at mode- entry and structural positions, such as <tool_call> and function names, can have disproportionate control over the global generation mode. We propose Soft Clamp, a per-token divergence calibration method that dynamically compresses extreme token-level Jensen-Shannon divergence while preserving nonzero gradients. On APIGen-MT, Soft Clamp reduces over-calling from 13.7% to 9.0% relative to vanilla GKD while matching its decision accuracy. In a BFCL multi-turn diagnostic, it also lowers tool-call loops and repeated calls among GKD variants. These results suggest that multi-teacher OPD should monitor where teacher signals act, not only how large they are in aggregate.

Jiabin Shen, Guang Chen, Chengjun Mao

LLM Tool UseMulti-Teacher Knowledge DistillationOn-Policy DistillationTool Use
AskPDF
Jul 7, 2026

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajectories, offering a promising framework for language agent training. However, its application to long-horizon agentic tasks remains insufficiently explored. We identify two key inefficiencies in vanilla agent OPD: (1) full-horizon rollouts often waste wall-clock resources on tail turns that provide weak and noisy KL supervision, and (2) trajectory-level KL objectives concentrate most of the loss on shallow tokens, leaving deeper decision turns under-trained once initial behaviors are aligned. To address these challenges, we propose TurnOPD, a turn-level budgeting strategy for efficient on-policy distillation of long-horizon agents. TurnOPD consists of two budget controllers: adaptive rollout-depth budgeting, which uses probe-based turn statistics to determine rollout length, and progressive turn-normalized loss budgeting, which gradually shifts KL weighting from token-level to turn-balanced supervision. Experiments on ALFWorld, WebShop, and Multi-Hop Search with task-specialized teacher models show that TurnOPD achieves superior validation accuracy under equal wall-clock training budgets and advances the accuracy--time frontier beyond vanilla OPD.

Yuhang Zhou, Kai Zheng, Haoling Li +3

Fudan University · Tencent Hunyuan

LLM Agent TrainingOn-Policy DistillationLong-Horizon LLM Agents
AskPDF
Jul 6, 2026

Weak-to-Strong Generalization via Direct On-Policy Distillation

Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training. As models scale, post-training itself becomes a bottleneck. We study a weak-to-strong alternative: run RL on a smaller model where rollouts are cheaper, then reuse what that RL run learned to improve a stronger target model. Directly distilling the post-RL weak teacher is not enough, because the teacher's final policy mixes useful RL gains with the limitations of the smaller model. We propose Direct On-Policy Distillation (Direct-OPD), which transfers the teacher's RL-induced policy shift instead. Direct-OPD compares the post-RL teacher with its own pre-RL reference and treats their log-ratio as a dense implicit reward for the student. In plain terms, the checkpoint pair tells us which actions RL made the weak model more or less likely to take, and Direct-OPD applies that signal on the stronger student's own on-policy states. This directly reuses the weak model's RL supervision signal without running sparse-reward RL on the target model. Empirically, Direct-OPD consistently leverages weaker teachers to improve stronger target models; notably, it boosts Qwen3-1.7B from 48.3% to 58.3% on AIME 2024 in just 4 hours on 8 A100 GPUs. It outperforms step-matched direct RL and enables the sequential composition of multiple policy shifts. Our results show that RL outcomes can be reused across model scales as implicit reward signals, not merely as final models to imitate.

Shiyuan Feng, Huan-ang Gao, Haohan Chi +7

1SIA-Lab of Tsinghua AIR and ByteDance Seed · Institute for AI Industry Research (AIR), Tsinghua University · 4Peking University +1

RL for Language Model ReasoningWeak-to-Strong GeneralizationReinforcement Learning with Verifiable RewardsOn-Policy DistillationPolicy Learning
AskPDF
Jul 6, 2026

Rethinking On-Policy Self-Distillation for Thinking Models

Self-distillation is a promising recipe for self-improvement in language models. In this setting, a model can serve as its own teacher when given privileged information, such as a solution to a math problem. This seems especially appealing for thinking models, which can use test-time reasoning to absorb the privileged information. Surprisingly, we show that privileged self-distillation degrades thinking models on long reasoning traces: across five Qwen3 and OLMo thinking models evaluated on AIME24, AIME25, and HMMT25, privileged-context distillation causes a relative drop of up to 17% in avg@16 accuracy. The degradation scales with the amount of privileged context withheld from the student and is most pronounced at long rollout budgets, where thinking models otherwise obtain their largest gains. This failure mode is not specific to self-distillation: on-policy distillation (OPD) improves thinking models, but privileged OPD reverses these gains. Our diagnostics link this failure mode to how privileged teacher context reshapes learning at high-entropy forking positions, where multiple continuations remain plausible and may lead to different reasoning paths. Privileged context lowers fork rates in thinking-model rollouts but not in instruction-model rollouts. This leads to an interesting dichotomy, where privileged context can help instruction-tuned models but hurts stronger thinking models. The effect is visible when the student begins a self-correction branch, where privileged OPD penalizes sampled reconsideration tokens that vanilla OPD supports. Thinking models trained with a privileged teacher produce fewer verification, backtracking, and hedging markers, even after length normalization. These findings indicate that self-distillation for strong thinking models requires attention to token-level signal, especially around correction and reasoning steps.

Simran Kaur, Narutatsu Ri, Yinghui He +2

Princeton Language and Intelligence, Princeton University

LLM Self-CorrectionOn-Policy Self-DistillationOn-Policy DistillationContext DistillationLearning Using Privileged InformationLarge Reasoning Models
AskPDF
Jul 6, 2026

Multi-Turn On-Policy Distillation with Prefix Replay

We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a teacher over these multi-turn interaction histories. Fully online OPD is costly because each update requires fresh student rollouts through the environment and teacher queries at visited histories. We propose Replayed-Prefix On-Policy Distillation (ReOPD), an off-environment alternative that reuses pre-collected teacher trajectories as replayed prefixes: the student acts at selected steps, while the teacher provides dense per-step supervision without executing new environment interactions. We show that multi-turn OPD introduces a prefix trap: making histories more student-on-policy improves relevance to the student, but can query the teacher on histories where its target is unreliable. This creates a two-sided distribution shift between student occupancy and teacher reliability. ReOPD addresses this by treating multi-turn OPD as a reliability-aware prefix distribution design and implements it with a simple step-decaying sampling schedule that emphasizes early, lower-shift prefixes. Across mathematical reasoning with Python and search environments over multiple teacher and student model scales, ReOPD preserves or improves OPD-level accuracy, uses zero tool calls during student training, and is at least 4×\times faster per rollout than OPD. ReOPD therefore turns expensive agent-environment interaction into a reusable offline resource, enabling scalable distillation across tools, tasks, and environments.

Baohao Liao, Hanze Dong, Christof Monz +3

1Microsoft Research · University of Amsterdam

LLM Agent TrainingOn-Policy DistillationPolicy LearningRL for LLM Agents
AskPDF
Jul 6, 2026

Trust Region Policy Distillation

Big goals are hard to achieve all at once; breaking them into small steps is wiser. We present Trust Region Policy Distillation (TOP-D), which transforms the notoriously unstable, high-variance On-Policy Distillation (OPD) into a stable training paradigm by dynamically constructing a proximal teacher. Theoretically, we establish a rigorous framework demonstrating that TOP-D inherently controls gradient variance. By providing a formal global convergence analysis alongside a monotonic improvement bound, we mathematically formalize the reliability and stability of the overall training dynamics. Empirically, TOP-D dramatically enhances training stability, sample efficiency, and final performance on mathematical reasoning tasks. More importantly, TOP-D introduces zero additional computational overhead, positioning itself as a promising alternative to the well-established OPD paradigm.

Zhengpeng Xie, Li Lyna Zhang, Zeke Xie +1

On-Policy DistillationPolicy LearningPolicy DistillationKnowledge DistillationRL Stability
AskPDF
Jul 5, 2026

UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning

Recent advances in multimodal foundation models and agent systems have driven GUI agents from single-platform task execution toward cross-platform interaction. However, building multi-platform GUI agents remains challenging. On one hand, high-quality and executable cross-platform interaction trajectories are still scarce, and existing data often suffer from limited platform coverage. On the other hand, different platforms exhibit distinct interaction conventions, making joint or continual training prone to behavioral pattern mixing, platform-specific capability degradation, and catastrophic forgetting. To address these challenges, we construct Uni-GUI, a high-quality cross-platform GUI interaction dataset, and propose UI-MOPD, the first method that incorporates multi-teacher on-policy distillation into continual learning for GUI agents. UI-MOPD dynamically selects a platform-specific teacher according to the current environment and transfers platform-specific behavioral priors to a shared policy through platform-conditioned distillation, enabling adaptation to new platforms while preserving capabilities on existing ones. Experiments on OSWorld and MobileWorld show that UI-MOPD achieves task success rates of 38.2% and 12.0%, respectively, demonstrating its effectiveness in balancing cross-platform capability retention and new-platform adaptation. Project page: https://elispectre.github.io/UI-MOPD/.

Niu Lian, Alan Chen, Zhehao Yu +8

Tsinghua Shenzhen International Graduate School, Tsinghua University · Harbin Institute of Technology, Shenzhen · Zhejiang University +2

Continual Learning for LLM AgentsGUI AgentsMulti-Teacher Knowledge DistillationOn-Policy Distillation
AskPDF
Jul 4, 2026

Reward-Gated On-Policy Distillation

On-policy distillation is a powerful way to transfer reasoning ability from a strong teacher to a smaller student: the student samples trajectories from its own policy, and the teacher provides dense token-level supervision on the states the student actually visits. However, this supervision is not always reliable: a teacher can assign high likelihood to plausible but incorrect solutions, or low likelihood to correct student solutions that follow different reasoning paths. Unconditionally distilling the teacher can therefore reinforce bad modes or erase useful student behavior. To address these limitations, we introduce RG-OPD: Reward-Gated On-Policy Distillation that uses verifier feedback to decide when teacher logits should be trusted. RG-OPD bridges sparse verifier rewards and dense teacher logits, preserving token-level supervision while filtering misleading teacher signals. Across reasoning and coding benchmarks, RG-OPD produces stronger distilled students, outperforming both vanilla reverse-KL distillation and the recent TSD-KD baseline. At 1K generation length, RG-OPD improves over reverse-KL by 2.9 points and over TSD-KD by 4.9 points; in the long-generation setting, it improves over the untuned student by 8.2 points. Our code is available at https://github.com/UoC-tail/RG-OPD.

Mohammad Sadegh Akhondzadeh, Vijay Lingam, Atula Tejaswi +3

University of Cologne · AWS AI · UT Austin +1

Language Model DistillationOn-Policy DistillationLLM Reasoning
AskPDF
Jul 2, 2026

Purified OPSD: On-Policy Self-Distillation Without Losing How to Think

On-policy self-distillation (OPSD) has emerged as a promising paradigm for improving LLM reasoning, where a privileged teacher with access to reference solutions provides token-level supervision on the student's own generated trajectories. However, we find that OPSD consistently fails on long chain-of-thought (long-CoT) reasoning models, yielding at best marginal gains while destabilizing the reflective reasoning capability these models depend on. Through a novel decomposition of the teacher's supervision signal, we identify the root cause: the teacher's supervision is dominated by a reference-induced component that drives rote memorization of reference-specific shortcuts, while the question-conditioned, inference-transferable component is ignored or actively opposed. Based on this diagnosis, we propose a two-step solution. First, we construct a reference-only teacher (the same model conditioned on the reference without the question) to isolate the non-transferable component of the supervision signal; the residual after subtracting this component captures the question-conditioned, inference-transferable correction. Second, we use pointwise mutual information (PMI) as the mechanism to transform this residual into a well-formed PMI target distribution that the student can directly distill from, filtering out the reference-induced shortcut. Experiments on four long-CoT models across two datasets demonstrate consistent improvements over both the base model and standard OPSD, while preserving the models' natural epistemic behavior throughout training.

Zhanming Shen, Jintao Tong, Shaotian Yan +9

1Zhejiang University · 2Tongyi Lab, Alibaba Group · 3Huazhong University of Science and Technology +1

CoT DistillationOn-Policy Self-DistillationCoT ReasoningOn-Policy DistillationLLM Reasoning
AskPDF
Jul 1, 2026

H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation

On-policy distillation (OPD) has recently emerged as an effective post-training paradigm by providing supervision on student-generated trajectories. However, existing OPD methods for multimodal reasoning usually rely on a static teacher routing, assigning each sample to a single teacher based on modality or task type. This ignores that visual grounding and abstract reasoning may dominate different decoding steps, making a single teacher insufficient for the full trajectory. To this end, H-OPD is proposed as a confidence-aware heterogeneous multi-teacher OPD framework for multimodal reasoning. By verifying the complementarity of heterogeneous teachers in the same reasoning process, H-OPD replaces task or sample level teacher routing with token-level teacher arbitration along the shared student trajectory. H-OPD employs vision-to-language description transfer to enable text-only teachers to access key visual semantics, and uses a confidence-aware arbitration mechanism to dynamically combine vision-language teacher and text-only teachers at each token. Extensive evaluations over 11 widely-used reasoning benchmarks showcase the superior performance of our method.

Qixiang Yin, Huanjin Yao, Yuchen Cai +4

Beijing University of Posts and Telecommunications · Zhongguancun Academy, Beijing, China · HKUST +2

Cross-Modal Knowledge DistillationVLM DistillationMultimodal ReasoningMulti-Teacher Knowledge DistillationOn-Policy DistillationMultimodal Understanding
AskPDF
Jun 29, 2026

Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback

Imitation Learning is a natural framework for learning in sequential decision-making systems and has emerged as the dominant paradigm through which we understand language model training. A central puzzle is that, while in theory offline IL can be horizon-free and optimal, in practice online methods such as on-policy distillation often outperform offline methods such as supervised fine-tuning. We propose a noisy expert model to explain this gap, in which the learner only has access to a noisy version of the expert's policy, but wishes to compete against the reward achieved by a clean expert, motivated by the fact that in many applications, e.g. training language models to perform long chains of thought, the expert is often imperfect. In this setting, we show a sharp separation between offline and online IL. Offline learning from noisy trajectories is fundamentally hard: to compete with the clean expert, the sample complexity must grow exponentially, in contradistinction to the clean expert setting where no explicit horizon dependence exists. In contrast, we prove that online interaction with the noisy expert via a novel variant of OPD enables polynomial dependence on the horizon in general. We further show that, under a natural condition on the expert noise distribution, which we show to be necessary for any horizon-free sample complexity, one can obtain such a guarantee, although our proposed algorithm sacrifices statistical efficiency in its dependence on the size of the policy class. Our analysis leads to an alternative loss function that is commonly considered empirically for LM training. We further provide algorithms and lower bounds, and extend our results to the more realistic setting of unknown corruption when the clean expert is deterministic, thereby providing a theoretical foundation for why OPD can outperform SFT when training language models from imperfect teachers.

Ved Sriraman, Peihan Liu, Daniel Hsu +1

Department of Computer Science, Columbia University · Department of Electrical Engineering, Columbia University

RL for Language ModelsImitation LearningOn-Policy Distillation
AskPDF
Jun 29, 2026

DOPD: Dual On-policy Distillation

On-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals. To furnish high-quality supervision sources and thereby elevate the performance frontier of distillation, an intuitive direction is to infuse privileged information to either teacher or student itself. However, this additional input induces a potential failure mode we dub privilege illusion: a pattern that conflates the transferable capability gap that students are meant to close, and the information asymmetry gap that can only be mimicked but never replicated. This issue is further amplified by the inherent non-uniformity of token-level supervision, where only a small subset of tokens carries pivotal capability-bearing signals. To this end, we propose DOPD, an advantage-aware dual distillation paradigm that dynamically routes token-level supervision between privileged teacher and privileged student policies based on their advantage gap and relative probabilities. Each token receives supervision of different strength, objective, and strategy from either teacher or student itself, which transfers credible capability while simultaneously receiving auxiliary signals, to alleviate privilege illusion. Extensive experiments on both large language model (LLM) and vision-language model (VLM) settings demonstrate that DOPD consistently outperforms Vanilla OPD and other counterparts. Further results on stability, robustness, continual learning, and out-of-distribution tasks validate its superiority.

Xinlei Yu, Gen Li, Qingyi Si +13

NUS · MMLab, CUHK · Explore Academy, JD +1

On-Policy Self-DistillationVLM DistillationLanguage Model DistillationOn-Policy Distillation
AskPDF
Jun 29, 2026

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon

Online imitation learning (IL), particularly on-policy distillation, has emerged as a strong LLM post-training approach, often outperforming offline supervised fine-tuning (SFT). Yet a principled understanding of when and why online interaction helps remains unclear. In this work, we challenge the view that error accumulation is the main source of online IL's advantage, and instead show that the benefits of online interaction depend critically on whether the setting is realizable, i.e., whether the student policy class can represent the expert policy. Under realizability, we empirically find that offline IL already matches expert performance. In contrast, in non-realizable (misspecified) settings, we prove that offline IL encounters an information-theoretic bottleneck even when horizon H=1H=1, and propose a structural characterization of misspecification relative to the reward, under which online IL provably achieves high performance despite a large distributional mismatch between the expert and student policies.

Huaqing Zhang, Jingchu Gai, Juno Kim +2

Tsinghua University · Carnegie Mellon University · UC Berkeley +1

Imitation LearningInteractive Imitation LearningOn-Policy DistillationLLM Post-Training
AskPDF
Jun 29, 2026

MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training

Modern large language models (LLMs) rely on reinforcement learning during post-training to push specific capabilities, yet integrating multiple capabilities into one model remains hard. Existing methods, such as Off-Policy Finetune and Mix-RL, are either inefficient or lose performance. In this work, we propose Multi-teacher On-Policy Distillation (MOPD), a post-training paradigm for combining the capabilities of multiple domain RL teachers: we first run per-domain specialised RL to obtain a set of domain teachers, then distill these teachers into the student on its own rollouts. This eliminates exposure bias and provides a dense optimization signal. On Qwen3-30B-A3B, MOPD outperforms Mix-RL, Cascade RL, Off-Policy Finetune, and Param-Merge baselines, inheriting nearly all of each teacher's capability. MOPD also enables parallel, independent development of domain teachers, removing the cross-domain coupling typical of multi-domain post-training. MOPD has been deployed in the post-training of MiMo-V2-Flash, an industrial-scale frontier model, demonstrating its practical value for capability integration in frontier-scale LLMs.

Wenhan Ma, Jianyu Wei, Liang Zhao +10

Peking University · Xiaomi · LLM Core, Xiaomi +2

Multi-Teacher Knowledge DistillationOn-Policy DistillationRL Post-TrainingLLM Post-TrainingLanguage Model Post-Training
AskPDF
Jun 29, 2026

Building Multi-Task Agentic LLMs via Two-Phase Distillation

A key step toward artificial general intelligence is to train models that can perform multiple tasks. In this paper, we study how to build such models by first training separate RL experts for individual tasks and then consolidating them via distillation, as an alternative to directly training a single model on mixed tasks. We show that off-policy distillation degrades in multi-task settings due to the mode-covering nature of forward KL: aggregating data from multiple tasks introduces a large number of behavioral modes that can exceed the student's capacity, forcing it to average across behaviors and leading to degraded performance. In contrast, on-policy distillation is mode-seeking but requires strong initialization. Inspired by these observations, we propose a two-phase approach: off-policy distillation followed by on-policy refinement. Evaluation across conversational agents and text-based games confirms that this two-phase approach matches single-task RL expert performance for each individual task, whereas off-policy or on-policy distillation alone fails to match this performance.

Huaijie Wang, Shusheng Xu, Yi Wu +1

Tsinghua University · Ant Group

Language Model DistillationMulti-Task RLOn-Policy DistillationRL for LLM Agents
AskPDF
Jun 28, 2026

CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning

Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss, using as its teacher the same policy conditioned on privileged context. The prevailing recipe gates this loss by a single scalar, the teacher-student log-probability gap. This signal is doubly limited: it is retrospective, scoring only the realised rollout and never the counterfactual ones, and it is sign-blind, never signalling when a teacher-preferred action would have harmed the trajectory. We introduce CRAFT, a three-pillar credit-assignment scheme that addresses both limitations. Pillar 1, Counterfactual Token Importance, reuses the G-1 sibling rollouts that GRPO already samples and importance-weights them by the log-probability gap to form a self-normalised estimate of the group-level counterfactual change in advantage from up-weighting teacher-preferred actions at each step; this yields a signed per-token credit at near-zero extra compute. Pillar 2 is an asymmetric controller that raises the distillation weight as it lowers the reference-KL weight along an exponential moving average of gate activity, and conversely. Pillar 3 polarises the KL penalty token by token, switching between a mode-seeking and a mode-covering update according to the sign of the credit. Each pillar has an independent switch that, when disabled, renders the loss and gradient byte-identical to the baseline in IEEE-754 arithmetic, so any measured gain is attributable to algorithmic change rather than implementation drift. We prove the estimator's consistency and a variance bound, give structural and bit-exact reproducibility guarantees, and evaluate CRAFT across three agentic environments, four model scales, and five end-to-end methods, plus two tabulated prior-work baselines. Among these is Adaptive-CRINGE, a comparator sharing Pillar 2 with CRAFT, isolating the counterfactual contribution.

Zibin Meng, Kani Chen

The Hong Kong University of Science and Technology

Agentic RLKL-Regularized RLCredit Assignment in RLStep-Level Credit Assignment in RLOn-Policy DistillationCounterfactual Credit Assignment
AskPDF
Jun 26, 2026

SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision

On-policy distillation (OPD) has a property absent in offline distillation and RL: teacher supervision quality depends on student competence. Incoherent rollouts yield noisy gradients; already-mastered tokens yield redundant ones. This creates waste at three scales (tokens, training phases, and prompts) yet existing methods supervise uniformly. We introduce SEAD, which uses entropy as a unified probe of this competence-dependent degradation at three scales: (1) joint teacher-student entropy partitions tokens into zones receiving tailored divergences or zero gradient (approx. 50% skipped); (2) a cosine schedule anneals from forward to reverse KL as competence grows; (3) a competence-gated curriculum introduces prompts easy-to-hard. These components are symbiotically necessary: token selection requires coherent rollouts (curriculum), annealing requires monotonic improvement (also curriculum). On OLMo-3 (7B to 32B), SEAD achieves +4.8 avg accuracy over vanilla OPD across six math benchmarks, with ablations confirming super-additive interactions.

Chia-Hsuan Lee, Zelei Cheng, Yu Wang +4

Capital One

Language Model DistillationOn-Policy DistillationKnowledge Distillation
AskPDF
Jun 26, 2026

ATOD: Annealed Turn-aware On-policy Distillation for Multi-turn Autonomous Agents

Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement. On-policy distillation (OPD) provides dense teacher guidance and typically improves rapidly in the early stage, but its gains saturate once the student approaches the teacher, limiting the final performance ceiling. Reinforcement learning (RL) directly optimizes environment rewards and encourages exploratory improvement toward a higher reward-defined ceiling, but sparse and delayed feedback makes early-stage learning much less efficient than OPD. In this paper, we propose ATOD (Annealed Turn-aware On-policy Distillation), a hybrid online distillation algorithm that explicitly exploits this complementarity. (1) ATOD uses an annealed OPD-RL schedule: OPD dominates early training to approach teacher-level behavior, while RL is gradually strengthened to drive reward-based exploration. (2) ATOD introduces Turn-level Disagreement-Uncertainty Reweighting (T-DUR), which softly amplifies high-utility turns and improves dense supervision in long trajectories. Experiments on ALFWorld, WebShop, and Search-QA show that ATOD consistently outperforms competing post-training baselines: across the three student sizes, ATOD improves average success rate by 3.03 points over OPD and 23.62 points over GRPO, while surpassing the corresponding teacher models by 2.16 points.

Qitai Tan, Zefang Zong, Yang Li +1

Tencent Inc. · Tsinghua University

Agentic RLOn-Policy DistillationRL Post-TrainingRL for LLM Agents
AskPDF
Jun 25, 2026

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Outcome-based reinforcement learning provides a stable optimization backbone for language agents, but its sparse trajectory-level rewards provide little guidance on which intermediate decisions should be reinforced or suppressed. On-policy self-distillation offers dense token-level supervision, yet existing skill-conditioned variants often rely on external skill memories or retrieved privileged context, which are costly to maintain and can be mismatched with the state distribution induced by the current policy in multi-turn interaction. We propose OPID (On-Policy Skill Distillation), a framework that extracts skill supervision directly from completed on-policy trajectories. OPID represents trajectory hindsight as hierarchical skills: episode-level skills capture global workflows or failure-avoidance rules, while step-level skills capture local decision knowledge at critical timesteps. A critical-first routing mechanism uses step-level skills when critical decisions are identified and falls back to episode-level skills as default guidance otherwise. The selected skill is injected into the interaction history, allowing the old policy to re-score the same sampled response under both original and skill-augmented contexts. The resulting log-probability shift yields a token-level self-distillation advantage, which is combined with the outcome advantage for policy optimization. OPID thus preserves RL as the primary training objective while introducing dense, distribution-matched hindsight supervision. Experiments on ALFWorld, WebShop and Search-based QA demonstrate that OPID generally improves agent performance, sample efficiency, and robustness over outcome-only RL and existing skill-distillation baselines. Our code is available at https://github.com/jinyangwu/OPID/tree/main.

Shuo Yang, Jinyang Wu, Zhengxi Lu +8

1Tsinghua University · 2Zhejiang University · 3The Chinese University of Hong Kong +2

Agentic RLLLM Agent Skill LearningOn-Policy DistillationPolicy Learning
AskPDF
Jun 25, 2026

NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research

Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization. This work presents NebulaExp, a fully transparent, ablation-driven post-training pipeline built on Qwen3-8B-base, covering two orthogonal model branches: general instruct model and complex reasoning-specialized model. We curate a raw corpus of 3.84M multi-source SFT samples and a 200K verifiable RL candidate pool, and design an end-to-end data processing stack including response distillation, multi-dimensional cross-verification filtering, fine-grained difficulty grading, task classification and diversity-aware sampling. For the Instruct branch, our three-stage optimized supervised fine-tuning approach NebulaExp-Ins-SFT improves the average benchmark score from the 55.01 baseline of Qwen3-8B-nothink to 60.99. GRPO reinforcement learning then further elevates the average score to 61.85. For the Reasoning branch, medium-difficulty GRPO RL improves average reasoning score from 73.88 to 75.17. To address RL's dependency on task verifiers, we systematically investigate single-teacher and multi-teacher OPD (MOPD): utilizing merely 4K instruction-following samples and outperforms RL baseline by 3.26 points on IFEval with +4.43 average overall gain; MOPD fuses four domain-specialist teachers with merely 10K samples, lifting average performance by 4.18 over the base model. This report provides a fully reproducible empirical post-training recipe for 8B-scale LLMs, and comprehensively dissects the capability trade-offs among instruction adherence, mathematical reasoning, code generation and general knowledge.

Qiaobo Hao, Yangqian Wu, Shunyi Wang +5

ZTE NebulaL0 Post-Training Team

Supervised Fine-TuningRL for Language ModelsLLM AlignmentOn-Policy DistillationLLM Post-Training
AskPDF
Jun 24, 2026

V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning

Fine-grained visual reasoning requires multimodal large language models (MLLMs) to identify task-relevant visual evidence and ground their reasoning in local image regions. Existing agentic methods typically rely on reinforcement learning with verifiable rewards or supervised fine-tuning on large-scale annotated reasoning traces, leading to costly exploration, hand-designed verification rules, or heavy dependence on textual supervision. A natural way to avoid such external answer labels is to learn from trajectories sampled by the student itself, which points to On-Policy Distillation (OPD). To understand what OPD can and cannot provide for visual reasoning, we revisit it as negative-free stop-gradient alignment. This perspective shows that, although OPD provides effective token-level correction, its ceiling is constrained by the absence of trajectory-level discrimination. Motivated by these observations, we propose V-Zero, an answer-label-free framework for visual reasoning with contrastive evidence gating. V-Zero uses no annotated textual answer labels; instead, during training it pairs a question-relevant regional crop with a negative visual view to evaluate student-sampled trajectories and gate dense token-level distillation. Experiments on multiple visual reasoning benchmarks show that V-Zero consistently improves fine-grained visual reasoning while preserving strong generalization. Notably, V-Zero is more than 5×\times faster than previous supervised fine-tuning methods and more than 10×\times faster than reinforcement learning baselines. Code and dataset will be released at https://github.com/eVI-group-SCU/V-Zero

Haoxiang Sun, Zhihang Yi, Langxuan Deng +6

Sichuan University · Xi’an Jiaotong University · TeleAI of China Telecom +1

Visual ReasoningVLM DistillationVision-Language GroundingVLM ReasoningVisually Grounded ReasoningOn-Policy Distillation
AskPDF
Jun 23, 2026

AsyncOPD: How Stale Can On-Policy Distillation Be?

On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training. Like reinforcement learning (RL), however, OPD faces an on-policy systems bottleneck, as rollouts can dominate training time for reasoning workloads. Asynchronous training pipelines can alleviate this bottleneck by decoupling rollout generation from learner updates, but doing so introduces stale-policy data. While prior work has studied stale data in asynchronous RL, its effects in OPD remain underexplored. We present the first systematic study of staleness in asynchronous OPD, focusing on a practical setting where teacher feedback is implemented through local KL losses and full-vocabulary teacher logits are too expensive to store or transfer, necessitating finite teacher-score caches. We first show that KL direction changes the stale-data problem: teacher-weighted forward KL is more robust to stale rollouts, whereas student-weighted reverse KL is vulnerable. Second, for this vulnerable reverse-KL case, we study whether methods designed to stabilize asynchronous RL can mitigate OPD staleness. In our experiments, they do not improve over a simpler OPD-specific surrogate: recomputing the reverse-KL signal under the current student at learner time. Third, we analyze how finite teacher-score caches create a bias-variance tradeoff for sparse and sampled reverse-KL OPD estimators. This motivates multi-sample Monte Carlo (MC), which preserves MC correctability while reducing one-sample variance. Finally, we present and open-source AsyncOPD, a fully asynchronous OPD training pipeline built from these estimator choices. Experiments show that AsyncOPD improves training throughput by 1.6×1.6\times to 3.8×3.8\times over strict synchronous training while reaching comparable accuracy.

Wonjun Kang, Kevin Galim, Seunghyuk Oh +9

FuriosaAI · Ajou University · UC Berkeley +3

Language Model DistillationOn-Policy DistillationLLM Post-TrainingTeacher-Student Learning
AskPDF
Jun 23, 2026

Blockwise Policy-Drift Gating for On-Policy Distillation

On-policy distillation (OPD) trains a student policy using teacher signals computed on trajectories sampled by the student itself. Recent work shows that sampled-token OPD can be fragile on long-horizon reasoning tasks and that local teacher-support matching is a simple and effective repair. This paper introduces blockwise policy-drift gating, a lightweight student-only old-current drift controller for OPD under rollout reuse. The method computes log-probability shifts between the behavior student and the current student on the sampled token path, aggregates these shifts over fixed blocks or spans, and uses the resulting detached, mean-normalized gates to reweight OPD position losses. It does not change teacher targets, teacher top-K supports, or the rollout policy. In a six-variant Qwen3 math reasoning benchmark with a uniform 200-step training budget for all trained variants, we use pass@8 as the primary problem-level solve-rate metric. Fixed 64-token block gating improves sampled-token OPD mean pass@8 from 0.4978 to 0.5160 across AIME24, AIME25, MATH500, and AMC23. On Teacher-TopK/LSM, Block64 gives the best four-benchmark mean pass@8 among trained students. The results identify local old-current policy drift as a practical control signal for reused OPD rollouts and motivate block-level gating as a simple default for improving solve-rate robustness.

Liwen Zheng, Haiyun Jiang

Independent Researcher

Language Model DistillationOn-Policy DistillationTeacher-Student LearningPolicy Learning
AskPDF
Jun 22, 2026

ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation

On-policy distillation (OPD) improves LLM reasoning by training a student model on its own generated outputs, but standard OPD treats all student-generated outputs (SGOs) equally regardless of their informativeness. We observe a consistent asymmetry in controlled filtering experiments: in both OPD and on-policy self distillation (OPSD), training only on incorrect SGOs outperforms training only on correct ones. Our further analysis suggests that models trained on correct-only SGOs tend to generate shorter reasoning traces and show weaker reflection behavior, while incorrect SGOs better preserve exploratory reasoning near the model's capability boundary. To exploit this signal without requiring full answer-containing rollouts, we introduce ReNIO, which Reweights Negative trajectory Importance for LLM On-policy distillation. By using the student-to-teacher probability ratio, ReNIO identifies pivotal tokens leading to wrong reasoning traces and aggregates their information into a normalized sample weight, inherently assigning larger weights to likely negative trajectories without observing the correctness of final-answer. Since Re-NIO only uses prefix-conditioned token probabilities, it preserves OPD's prefix training advantage over full-rollout reinforcement learning. Across both mathematical reasoning and code generation tasks, ReNIO improves both OPD and OPSD, with representative relative gains of up to 8.90% for Qwen3-1.7B and 10.00% for R1-Distill-Qwen-7B on mathematical reasoning benchmarks. Code repo: https://github.com/BDML-lab/ReNIO.

Chen Lin, Kedi Chen, Wei Zhang

East China Normal University · Shanghai Innovation Institute

CoT DistillationLanguage Model DistillationOn-Policy DistillationLLM Reasoning
AskPDF
Jun 22, 2026

Finding the Evidence: Discovering Decision-Supporting Tokens for On-Policy Reasoning Distillation

On-policy distillation transfers reasoning ability through dense token-level supervision, yet the nature of the transferable signal remains unclear. We discover that reasoning chains contain two types of knowledge that require different discovery mechanisms: decisions (where to branch), which surface through student uncertainty, and evidence (intermediate steps that justify decisions), which hides in positions where the student is confident yet wrong. Current methods capture only decisions; the substantive knowledge in evidence tokens remains untransferred. We propose DEAR(Decision-Evidence Aware Reasoning Distillation), which first identifies decisions via student entropy, then discovers their supporting evidence through hidden-state cosine similarity to decision anchors, boosted by teacher-student divergence to prioritize the largest knowledge gaps. Across three student-teacher configurations on math and code benchmarks, DEAR consistently outperforms standard OPD, with up to +2.5pp on competition math and +5.7pp on code generation.

Jinwei Xiao, Zhuowen Han, Yueqing Sun +6

Meituan Longcat Team · TJUNLP Lab, College of Intelligence and Computing, Tianjin University · Nanjing University

CoT DistillationOn-Policy DistillationTeacher-Student LearningKnowledge DistillationAlgorithmic ReasoningLLM Reasoning
AskPDF
Jun 22, 2026

A Formula-Driven Survey and Research Agenda for On-Policy Distillation

On-policy distillation (OPD) trains an LLM on states induced by the current or recent student policy: the student generates complete or partial rollouts, a teacher or self-teacher scores the resulting tokens under their generated contexts, and dense log-probability, logit, or distributional signals are converted into post-training updates. This survey studies OPD as a feedback-to-update problem rather than a single loss family. We develop a formula-driven taxonomy from two routes -- direct distributional losses and policy-gradient-style log-ratio updates -- and use it to organize core methods, verifier- or outcome-guided hybrids, industrial reports, framework implementations, failure modes, and stabilization recipes under explicit evidence boundaries. The taxonomy shows that OPD effectiveness depends not only on KL direction or teacher access, but also on state compatibility, support construction, temporal credit, vocabulary-level probability routing, gates and weights, and regularization. We further separate two mechanisms often conflated in sampled-token OPD stability discussions. Temporal credit asks how teacher-student log-ratio returns should weight sampled actions across a rollout; vocabulary routing asks where probability mass should move when negative feedback suppresses a sampled token. This distinction yields bias boundaries for immediate, return-to-go, discounted, and baseline-corrected estimators, motivates GAE-OPD as a value-based hypothesis for log-ratio returns, and motivates Counterfactual Routed OPD (CR-OPD) for routing probability mass toward teacher-supported, student-reachable alternatives. We close by mapping actionability diagnostics, failure mechanisms, case studies, open problems, and a reporting checklist onto the same feedback-to-update variables.

Bowen Zhang

Tsinghua University

Language Model DistillationOn-Policy DistillationRL Post-TrainingTeacher-Student Learning
AskPDF
Jun 21, 2026

On the Position Bias of On-Policy Distillation

On-Policy Distillation (OPD) improves the learning efficiency of standard reinforcement learning through dense, token-level supervision from teachers. In the standard KL objective of OPD, token-level losses are uniformly averaged, implying equal weights for all tokens. However, we discover that not all tokens are created equal: as student rollouts grow longer, they deviate further from the teacher's distribution, leading to degraded supervision quality at later positions. As a result, OPD using only the first 30% of tokens can perform comparably to using all tokens, whereas OPD using only the last 30% of tokens barely learns anything. In this work, we provide a principled understanding of this issue through the lens of constrained optimization. Based on these insights, we derive Importance-Weighted On-Policy Distillation (IW-OPD), in which the weight assigned to each token depends on the accumulated discrepancy between the student's and teacher's distributions, naturally upweighting earlier tokens and downweighting later ones with larger deviations. We show that IW-OPD converges significantly faster than OPD, with better learning efficiency, and achieves better final performance than standard OPD in both same-size and cross-scale settings, improving performance up to 6.9 points on AIME-2025.

Yan Xie, Sijie Zhu, Tiansheng Wen +2

Xidian University · Georgia Institute of Technology · Amazon AGI SF Lab

Importance WeightingLanguage Model DistillationOn-Policy DistillationRL Post-TrainingTeacher-Student LearningPolicy Learning
AskPDF
Jun 20, 2026

Prefix-Guided On-Policy Distillation: Mining Golden Trajectories from Rollouts

On-policy distillation (OPD) improves reasoning models by applying dense teacher supervision on student-sampled trajectories. However, scaling OPD to long-horizon mathematical reasoning exposes a reliability and efficiency problem: standard OPD assigns every sampled candidate the same long rollout budget, even though some trajectories may quickly become weakly aligned with the teacher and provide less useful supervision. Prior analyses suggest that successful OPD depends on local teacher-student compatibility, which can be measured by top-k overlap on student-visited prefixes. When this overlap is low, continuing to generate or train on long suffixes may waste computation and introduce noisy learning signal. To address this, we introduce Prefix-Guided On-Policy Distillation (PG-OPD), a simple rollout-allocation framework that uses fixed-length prefixes to estimate trajectory value before expensive long-horizon generation. PG-OPD first decodes every sampled candidate to the same prefix length, computes teacher-student top-k overlap within an early probe window of that prefix, and selectively continues high-overlap candidates to a fixed long length. Low-overlap candidates stop at the fixed prefix, avoiding unnecessary suffix generation. Across diverse teacher-student combinations on AMC, AIME, and HMMT benchmarks, PG-OPD improves average accuracy by up to 4.80 points while reducing training time by up to 2.46x. These results suggest that prefix-level compatibility provides a practical signal for directing OPD computation toward trajectories that remain learnable from the teacher.

Qingfei Zhao, Huan Song, Shuyu Tian +2

TeleAI · Shanghai Jiao Tong University

Trajectory GenerationCoT DistillationMathematical ReasoningLanguage Model DistillationOn-Policy DistillationTeacher-Student Learning
AskPDF