On-Policy Distillation

Follow this topic Ask about this topic

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

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

Jul 30, 2026

Contrastive Reinforced Policy Optimization via Privileged Self-Distillation

Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD). While OPSD provides dense, logit-level supervision, it inherently suffers from exposure bias due to the privileged information of the self-teacher. In multi-turn agentic settings, this leads to reasoning route convergence and the loss of clear optimization directions. To tackle these challenges, we introduce Contrastive Reinforced Policy Optimization (CRPO), which reformulates agentic OPSD from a contrastive learning perspective. By leveraging predictive entropy to distinguish between positive positions (reflective exploration) and negative positions (exposure bias), CRPO conducts group-wise contrast to preserve reliable, fine-grained optimization signals. Extensive evaluations across 13 challenging reasoning and deep-search benchmarks demonstrate that CRPO consistently outperforms existing reinforcement learning and self-distillation baselines, significantly enhancing training stability and generalization in long-horizon interactions.

Xingjian Wu, Junlin Liu, Xingchen Liu +6

Meituan

Agentic RL RL for Language Model Reasoning On-Policy Distillation RL Post-Training Contrastive RL

Jul 30, 2026

Flux-OPD: On-Policy Distillation with Evolving Contexts

Large language model training in open-ended domains lacks verifiable rewards, making task preferences difficult to formalize as effective supervision. Contexts derived from task feedback can provide richer supervision, yet fixed contexts cannot adapt as the student evolves, motivating contexts that evolve with student performance. However, directly using evolving contexts as in-training supervision results in unstable distillation targets and conflicting distributions, requiring mechanisms to stabilize the target and downweight conflicts. In this paper, we characterize context distillation through a reverse-KL decomposition, showing that the student is distilled toward the geometric mean of context-conditioned teachers, while the objective contains a conflict term measuring disagreement among these teachers. Motivated by this characterization, we propose Flux-OPD, an OPD paradigm that uses evolving contexts as in-training supervision to incorporate contextual signals derived from task feedback. Flux-OPD treats differences between context-conditioned and context-free teachers as contextual difference signals, injects them as contextual corrections into the context-free teacher, and weights the correction strength using the conflict term. Experiments show that Flux-OPD achieves the best results among OPD paradigms, highlighting the potential of combining teacher supervision with evolving contexts as in-training supervision.

Yuran Wang, Zekun Wang, Bohan Zeng +10

Peking University · Kling Team · Tsinghua University +3

Language Model Distillation On-Policy Distillation Context Distillation Knowledge Distillation

Jul 30, 2026

From Scoring to Acting: Outcome-Verified Comparative Self-Distillation for LLM Agents

Recent work on LLM agents is shifting from external capability elicitation to capability internalization, enabling agents to retain useful skills without retrieval at inference time. On-policy self-distillation (OPSD) offers a promising direction, but many existing methods typically supervise students by scoring actions along student-generated trajectories. Such supervision has two limitations: teacher preferences are not validated by environment outcomes, and action-level scores underuse information from student rollouts, teacher rollouts, and their behavioral relationship. We therefore advocate outcome-verified teacher supervision and comparative learning over teacher-student trajectories. Based on this view, we propose Outcome-Verified Comparative Self-Distillation (OVCSD). OVCSD organizes failed student rollouts into a prefix tree, adaptively invokes a skill-conditioned teacher from student-reached states, and retains only outcome-verified successful continuations. It then applies localized comparative learning at the first state-aligned divergence and distills the post-divergence teacher suffix to transfer completion behavior. Experiments on ALFWorld and WebShop across three model scales show that OVCSD consistently outperforms skill-free RL and existing self-distillation baselines, achieving up to 29.7 and 5.4 absolute success-rate gains over the strongest baselines on ALFWorld and WebShop, respectively, while adding less than 3% privileged interaction during training.

Xu Xia, Jinghua Piao, Min Yang +3

Southeast University · Zhongguancun Academy · Tsinghua University +2

LLM Agent Skill Learning Self-Distillation On-Policy Distillation

Jul 30, 2026

Beyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold

A single reinforcement-learning run can produce a strong reasoner yet an incomplete teacher: it often amplifies only a subset of the valid solution modes. We argue that reinforcement learning (RL)-trained policies should therefore be viewed as local probes of a multi-basin reasoning solution manifold, rather than as globally reliable supervisors. Based on this view, we propose an expand-then-compress framework that couples teacher construction with multi-teacher policy distillation. In the expansion stage, Residual Group Relative Policy Optimization (RGRPO) trains a sequence of teachers from a common initialization and redirects each later round toward examples not yet covered by the accumulated teacher union. In the compression stage, reliability-gated Teacher-Union On-policy Distillation (TU-OPD) lets the student learn from its own response prefixes. For each example, only reliable teachers contribute, and their sampled-token OPD losses are weighted by their per-example quality. We further introduce Consensus-Residual Decomposition, which preserves a winner teacher's excess token preferences over its reliable peers, preventing specialist behavior from being suppressed during teacher aggregation. Experiments on mathematical reasoning, code generation, and instruction following show that the resulting Qwen3-1.7B student consistently outperforms the strongest individual teacher across all three domains, yielding relative improvements of 2.0%, 8.3%, and 6.9%, respectively, while retaining single-model inference. These results establish a simple but powerful principle: stronger students can be obtained not by selecting a single better teacher, but by deliberately constructing and compressing a complementary teacher union.

Songshuo Lu, Zhi Chen, Yaohua Tang

Moore Threads AI

RL for Language Model Reasoning Multi-Teacher Knowledge Distillation On-Policy Distillation

Jul 29, 2026

Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection

The growing capability of image generation models has made synthetic images a routine presence in open media, making robust and generalizable AI-Generated Image (AIGI) detection increasingly essential. While multi-modal large language models (MLLMs) offer a transparent alternative to black-box binary scoring, we observe that current MLLM-based detectors still exhibit notable perception bottlenecks in capturing fine-grained anomalies. They primarily focus on how visual evidence is organized and synthesized, leaving the intrinsic perception less optimized. To mitigate this gap, we present Veritas++, a perception-enhanced reasoning framework that establishes reliable perception as the foundation of authenticity reasoning. Rather than directly optimizing the model's explanatory ability, we ground AIGI detection on three basic perception abilities, i.e., capturing fine-grained visual details, semantic anomalies and pixel-level differences. Building on this insight, we introduce Perception-oriented Learning (PoRL), which replaces open-ended description supervision with verifiable rewards to explicitly strengthen these capacities. To further integrate enhanced perception with reasoning, we introduce Value-aware On-Policy Distillation (VaOPD), an adaptive distillation mechanism that prioritizes high-value distillation signals over uniform supervision, internalizing perception-aware reasoning through a privileged self-teacher. Extensive experiments across standard, in-the-wild and emerging benchmarks demonstrate that Veritas++ achieves promising generalization. The perception learning effectively bridges the perception gap and yields seamless gains on detection, while VaOPD further enables efficient capability evolvement without sacrificing existing performance. Code and checkpoints are available at https://github.com/EricTan7/VeritasPP.

Hao Tan, Jun Lan, Zichang Tan +7

School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences (UCAS), Beijing 101408, China, and also with the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation Chinese Academy of Sciences (CASIA), Beijing 100190, China · State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing 100190, China · Ant Group +2

VLM Distillation Large Vision-Language Models AI-Generated Image Detection On-Policy Distillation

Jul 29, 2026

On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment

Fine-tuning is the dominant paradigm for specializing large language models (LLMs), yet it exposes a critical vulnerability: malicious data providers can embed harmful behaviors into downstream corpora, creating models that retain professional skills while violating human values on demand. Existing safety-realignment defenses often fail in practice due to three key limitations: they frequently cause catastrophic forgetting of specialized skills; their effectiveness collapses when the defender cannot observe the attacker's prompt template; and successfully realigned models remain susceptible to re-jailbreaking via simple system prompt switches. To address these challenges, we propose Routing-based On-Policy Distillation (ROPD), a novel realignment framework that models the divergence between aligned and compromised output probability distributions rather than fitting specific prompt templates. We conduct extensive experiments comparing ROPD against four state-of-the-art baselines across three datasets and three base models with varying alignment strengths. Our results demonstrate that when baseline defenses face template mismatches, often accompanied by severe degradation in downstream task performance. In contrast, ROPD substantially mitigates template-mismatch risks, maintaining superior robustness in both defense effectiveness and capability preservation. While our analysis indicates ROPD is not entirely immune to template shifts, its performance degradation is negligible compared to existing methods, establishing a new standard for robust LLM realignment.

Yongjian Guo, Wanlun Ma, Lingyu Shen +2

Tsinghua University · Swinburne University of Technology · EPFL

LLM Safety Alignment Adversarial Robustness of Language Models On-Policy Distillation

Jul 28, 2026

Weak-to-Strong On-Policy Distillation

On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm for transferring capabilities across LLMs. Prevailing approaches assume a teacher at least as capable as the student: they either distill a larger model into a smaller one, which fails at the frontier where no larger teacher exists, or consolidate multiple domain experts trained from a shared base, which requires costly training at the student's scale. We introduce Weak-to-Strong On-Policy Distillation (W2S-OPD), a simple yet effective OPD framework that improves the strong student by distilling from multiple weak models. W2S-OPD constructs a proxy teacher in logit space from a contrast pair of a positive and a negative model, both smaller than the student and cheap to obtain. Their logit difference isolates the capability direction, which is added to the student's own base model, yielding a proxy teacher that couples this direction while staying distributionally adjacent to the student. The student then distills it by minimizing the per-token reverse KL on its own rollouts. We instantiate the contrast pair as i) a post-RL expert against its pre-RL initialization, isolating the skill RL instills, ii) a larger against a smaller base model, isolating the capability from scale, and iii) a small base model with correct versus wrong hints, isolating the instance-level direction toward the solution. Across four math and three code benchmarks, W2S-OPD outperforms OPD, enables the student to surpass the domain teacher, and keeps improving the student even when every supervision source is weaker. Analysis shows different contrasts yield distinct signals: the post-RL and hint contrasts emphasize reasoning frameworks, while the scale contrast emphasizes the solving procedure. Our code will be available at https://github.com/Yu-Fangxu/W2S-OPD.

Fangxu Yu, Weijia Xu, Michael Xu +2

University of Maryland, College Park · Microsoft Research · MBZUAI

Language Model Distillation On-Policy Distillation Knowledge Distillation

Jul 28, 2026

Pass the Baton: Trajectory-Relayed On-Policy Distillation

On-policy distillation (OPD) grounds token-level supervision in the student's own trajectory, yet suffers from prefix failure: once the student commits to a wrong reasoning direction, all subsequent generation builds on this deviation, producing misdirected continuations that elicit unreliable supervision and waste compute. We identify a teacher-student continuation asymmetry on failed prefixes, where the teacher tends to redirect while the student continues along the original direction, and convert it into a label-free handoff trigger in Relay On-Policy Distillation (Relay-OPD). During training, Relay-OPD constructs relay trajectories by letting the teacher briefly take over at detected trigger points to produce a teacher leg, after which the student resumes and is optimized on the resulting trajectory. A limited relay budget concentrates intervention on critical early positions while limiting departure from the student policy. With a Qwen3-4B-Instruct-2507 teacher and Qwen3-0.6B/1.7B-Non-Thinking students on eight mathematical reasoning benchmarks, Relay-OPD achieves the best or second-best results on every benchmark, outperforming standard OPD by +5.73% and the strongest baseline FastOPD by +1.49% on average for 1.7B, with consistent gains at 0.6B. Training trajectory length is reduced by over 50%.

Haolei Xu, Xiaowen Xu, Haiwen Hong +5

1Zhejiang University · 2Yuvion Team, Alibaba Group

Language Model Distillation On-Policy Distillation Policy Learning

Jul 27, 2026

Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation

On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guidance (CFG), a default component of modern diffusion systems, remains poorly understood. Existing OPD methods naturally extend velocity matching to the CFG-composed prediction, directly matching teacher and student guided velocities. We show that this objective is under-identified at the branch level: positive- and negative-branch errors can compensate in the guided prediction. Through two contrasting cases, we find that naive matching remains effective under shared negative conditioning, where both branch errors decrease jointly. When the model's native CFG schema retains privileged information in the teacher's negative branch that is unavailable to the student, however, this joint reduction breaks down and the composed objective induces antagonistic branch-error dynamics, reducing the positive-branch error while increasing the negative-branch error. We term this failure mode Negative Branch Asymmetry (NBA). To address NBA, we introduce Positive--Direction Matching (PDM), a branch-aware OPD objective that separately constrains the positive prediction and the CFG conditional direction. We apply PDM to dense-to-sparse video control, where naive guided matching is highly sensitive to inference guidance scales, while branch-aware supervision enables more robust and effective knowledge transfer.

Bingnan Li, Haozhe Wang, Haozhong Xiong +5

Qwen Business Unit of Alibaba

Diffusion Model Guidance Classifier-Free Guidance Diffusion Model Distillation On-Policy Distillation

Jul 27, 2026

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

Multi-turn long-horizon planning is critical for foundation model agents, yet how to fundamentally improve it remains unclear. Existing models are trained on uncontrollable and opaque Internet data, making it difficult to identify how planning ability is acquired, shaped, and integrated. To address this challenge, we introduce a unified and controlled multi-turn environment that enables precise control. It allows systematically study long-horizon planning across three stages. (1) Planning ability acquisition during pre-training. We study data format, distribution, and quality. Explicit world model construction through CoT state transition modeling yields stronger long-horizon generalization. Atomic skills alone are insufficient for compositional generalization, whereas a litte long-horizon data works. Moreover, suboptimal trajectories severely impair performance because errors amplify over long horizons. (2) Planning ability shaping via GRPO and OPD post-training. Through mutual information, we distinguish general planning patterns from task-specific planning knowledge. For planning patterns, we identify three application regions of post-training: unnecessary, effective, and unsupported. OPD has a broader effective region than GRPO under low-quality and long-horizon settings, as it provides more consistent update directions. For planning knowledge, distilling unseen procedures from a teacher with different knowledge may impair student's prior world modeling without fully establishing new knowledge. (3) Planning ability integration through MOPD post-training. We show that multi-teacher on-policy distillation (MOPD) integrates capabilities by converging to shared planning-pattern across environments. Compatible patterns enable cross-environment generalization, partially shared patterns support continual learning, while completely conflicting patterns cause severe interference.

Tianyi Men, Zhuoran Jin, Kang Liu +1

The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China

LLM Planning Long-Horizon Planning On-Policy Distillation Knowledge Distillation

Jul 27, 2026

FlowCTS: On-policy Continuous Trajectory Supervision of Flow Models

While on-policy distillation (OPD) effectively addresses sparse rewards and exposure bias in large language model post-training, its extension to flow models remains underexplored. To this end, we propose Flow Continuous Trajectory Supervision (FlowCTS), which matches subsequent student and reference trajectories initialized from the same student-visited state. Using the integral relation between trajectories and velocity fields, we derive a temporally weighted velocity-matching upper bound and discretize it into practical objectives parameterized by the number of supervision steps. Under a multi-reference setup, single-state FlowCTS-OPD outperforms vanilla KL-based OPD with faster convergence. FlowCTS-OPD improves GenEval from 0.90 to 0.93, OCR from 0.90 to 0.92, and PickScore from 22.75 to 23.06, while outperforming a mixed-reward RL baseline across all target metrics. Further analysis reveals a clear temporal supervision mismatch in vanilla KL-based OPD arising from its auxiliary SDE transition kernels. Beyond on-policy setting,FlowCTS also consistently outperforms vanilla SFT , particularly on OCR, while increasing supervision steps exhibit a trade-off between richer trajectory information and greater optimization difficulty.

Kaiyang Ye, Yuan Ge, Junxiang Zhang +8

Northeastern University · NiuTrans Research · Kunming University of Science and Technology

T2I Generation Flow-Based Generative Modeling On-Policy Distillation Knowledge Distillation

Jul 27, 2026

RP-OPSD: Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models

On-Policy Self-Distillation (OPSD) uses privileged information available only to the teacher to provide dense token-level supervision on trajectories generated by the student. However, existing methods often rely on verified solution traces, explanations generated by external models, or manually localized visual evidence, which limits their scalable application to multimodal large language models. To address this issue, we exploit the information gap between high- and low-resolution views of the same image and propose RP-OPSD (Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models). During training, the student policy generates on-policy trajectories from images at one-quarter of the original resolution, while the teacher policy provides supervision using the original-resolution images. By minimizing the divergence between their output distributions along the student trajectories, the student learns the predictive behavior of the teacher under high-resolution inputs, thereby strengthening its low-resolution capability and transferring the learned improvement to original-resolution inference. RP-OPSD requires neither additional human annotations nor external models to generate solution traces but only image--question pairs. Experiments on Qwen3.5-9B show that RP-OPSD achieves a 5.45% relative improvement in average performance at the original resolution and a

1.78\times

training speedup over OPSD. These results demonstrate that resolution differences can serve as a simple and scalable source of privileged information, providing an effective and efficient approach to on-policy self-distillation for multimodal large language models.

Qihui Zhu, Yuchen Wang, Zijian Wen +7

University of Science and Technology of China · 2ChangXin Memory Technologies, Inc.

Multimodal Large Language Models Self-Distillation On-Policy Distillation

Jul 26, 2026

Outcome-Confounded Local Supervision in On-Policy Distillation

On-policy distillation (OPD) trains a student on its own trajectories while a teacher supplies dense token-level likelihoods at student-visited prefixes. These likelihoods are often read locally: agreement appears safe to imitate, whereas disagreement appears to identify an error. We show that both readings are confounded by the outcome of the completed trajectory. We introduce an outcome-resolved diagnostic that crosses pointwise teacher-student divergence with final-answer correctness, separating safe imitation, productive divergence, harmful divergence, and agreement-on-failure. In an eight-seed mathematical-reasoning study with a Qwen3-8B student and Qwen3-32B teacher, agreement-on-failure constitutes 67.84% of pooled response-token mass; with a Qwen2.5-7B/32B pair it remains 67.68%. The result persists across threshold, sequence-level, format, and truncation audits. Even on prompts that the Qwen3 teacher solves in all four independent attempts, student accuracy rises to 86.91% but agreement-on-failure remains 14.76%. We then run three matched training probes that use the available signals to imitate, mask, or contrast whole trajectories; none consistently reduces agreement-on-failure. The result points to a localization limitation: local divergence paired with a trajectory-level outcome does not identify where a failed trajectory became unrecoverable. Addressing this limitation requires additional positional information, such as process labels, teacher continuations from student prefixes, or token-level alignment across rollouts. Our contribution is therefore diagnostic rather than a new training method.

Guoqing Ma

The Chinese University of Hong Kong, Shenzhen

Credit Assignment in RL Language Model Distillation On-Policy Distillation

Jul 24, 2026

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization

Open-weight language models from different families exhibit complementary capabilities, motivating their consolidation into a compact student through on-policy distillation (OPD). However, full-vocabulary OPD typically assumes a shared tokenizer, while existing cross-tokenizer methods may discard teacher probability mass or assign it to student tokens with unrelated content. We introduce Byte-Prefix Marginalization (BPM), which re-expresses the teacher's next-token distribution over the student vocabulary in a shared byte space. Specifically, BPM assigns each teacher token's probability to the longest student token whose byte representation is a prefix of the teacher token's bytes, aggregates mass mapped to the same student token, and places otherwise unmatched mass in an explicit residual category. This produces a vocabulary-complete, byte-aligned, and mass-preserving target for dense OPD. The target exactly recovers the teacher-induced byte-prefix marginal when the relevant prefix does not span multiple teacher tokens (a condition satisfied at more than 99% of training positions) and uses a mass-preserving, chain-factorized lower bound otherwise. Across Qwen3-32B, GLM-Z1-9B-0414, and MiniMax-M2.7 as teachers, BPM consistently outperforms current cross-tokenizer methods on six mathematics and programming benchmarks, improving six-benchmark avg@8 by 3.7-6.6 points over the strongest baselines.

Hao Wang, Kun Yuan, Wenlin Zhong +4

University of Chinese Academy of Sciences · KwaiKAT Team · Zhejiang University +1

Cross-Tokenizer Knowledge Distillation LLM Compression Language Model Distillation On-Policy Distillation Knowledge Distillation

Jul 23, 2026

X $^3$ -OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment

While large audio-language models have achieved remarkable progress in auditory perception, they still lag behind text-based large language models in deep logical reasoning, primarily due to the scarcity of high-quality audio reasoning data. To bridge this gap, we propose X

^3

-OPD, a cross-modal on-policy distillation framework that transfers reasoning capabilities from a powerful text teacher to an audio-language student. During training, the student generates reasoning trajectories conditioned on its own acoustic perception, while the teacher provides token-level guidance using matched textual inputs and verified answers. We further construct a three-tier symmetric corpus covering textual reasoning rendered into speech, audio-event reasoning grounded in complex acoustic scenes, and spoken-dialogue reasoning involving paralinguistic cues. This design extends cross-modal distillation beyond textually recoverable content to reasoning grounded in non-linguistic events, prosody, and conversational context. Experiments on MMSU, MMAU, BIG Bench Audio, and MMAR demonstrate that X

^3

-OPD substantially improves audio-grounded reasoning and chain-of-thought quality while largely preserving the model's existing capabilities under domain shift.

Dongjie Fu, Di Cao, Xize Cheng +6

1Tencent Hunyuan · 2Zhejiang University

Cross-Modal Knowledge Distillation Audio Reasoning Audio-Language Models Language Model Distillation On-Policy Distillation

Jul 23, 2026

OPOD: On-Policy Omni Distillation

Omni-modal models provide a unified interface for text, images, and audio. However, improving these abilities together remains difficult, as post-training on pooled multimodal data often fails to preserve the strengths of modality teachers. On-policy distillation (OPD) has recently become popular in model post-training. It samples responses from the current student and compares the teacher's and student's next-token distributions along those responses, yielding dense supervision while reducing the mismatch between training and inference. Despite these advantages, standard OPD does not readily extend to several modality teachers. Their guidance may favor conflicting changes to the shared model, while matching each teacher's next-token distribution can prevent the student from moving beyond that teacher. To address these challenges, we propose On-Policy Omni Distillation (OPOD), which consolidates text, image, and audio teachers into one omni model. OPOD routes each response to the corresponding teacher, controls the teachers independently, and applies guidance only when the teacher assigns a higher probability to the generated token. The selected teacher also evaluates answer confidence and whether the reasoning increases support for the answer. Extensive experiments on twelve benchmarks show that OPOD achieves the best average at three model scales, reaching 70.8, 51.7, and 46.2 and outperforming the strongest comparator by 2.1, 1.8, and 1.7 points. At 30B, it surpasses the base model and pooled RL training on all twelve benchmarks, and ranks first or second on eleven even when the teachers are included. Only the student is retained for deployment.

Tong Zhao, Yuyang Hu, Yutao Zhu +5

1Renmin University of China · 2Tencent

Cross-Modal Knowledge Distillation Unified Multimodal Models Multimodal Optimization Multi-Teacher Knowledge Distillation On-Policy Distillation Multimodal Foundation Models+1

Jul 22, 2026

SOPD-SocialNav: Selective On-Policy Distillation for Vision-Language Social Navigation

Vision-language models have shown strong potential for social robot navigation by leveraging rich semantic understanding of complex environments and human behaviors. However, large scale VLMs are difficult to deploy on resource-constrained robotic platforms, while lightweight VLMs often lack sufficient social reasoning capability. To address this problem, we propose SOPD-SocialNav, a selective on-policy distillation (SOPD) method that transfers social navigation knowledge from a large teacher VLM to a lightweight student VLM. SOPD introduces an entropy-based token selection mechanism that uses teacher uncertainty to identify socially informative decision tokens, while suppressing gradients from low-entropy tokens corresponding to trivial navigation states. A temperature-controlled Jensen-Shannon divergence objective is then used to align the student and teacher distributions on the selected tokens. Experiments on the SNEI and MUSON benchmarks demonstrate that SOPD consistently outperforms supervised fine-tuning, off-policy distillation, and standard on-policy distillation baselines in action prediction, perception consistency, and reasoning consistency. Real-world deployment on a Scout Mini robot further shows that the distilled model can generate more socially appropriate navigation behaviors in conversational and queuing scenarios. These results suggest that SOPD is an effective strategy for building lightweight yet socially aware VLM-based navigation systems.

Xinyu Zhang, Zishuo Wang, Ling Xiao

Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan

Efficient VLM Inference VLM Distillation Social Robot Navigation On-Policy Distillation VLMs for Robotics

Jul 21, 2026

AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified by the target model, has become a prevalent paradigm for accelerating large language model inference. Recent work such as DFlash further boosts drafting efficiency by leveraging diffusion drafters, whose parallel denoising mechanism enables draft generation in a single forward pass. In this work, we uncover a central pitfall of diffusion drafters: bidirectional attention is a double-edged sword. On one hand, it endows the model with parallel generation and global contextual modeling capabilities; on the other hand, this inherent global dependency introduces high variance at both the domain-level and the token-level: acceptance rates fluctuate substantially across different domains, and draft token quality also varies heterogeneously at different token positions. To tackle this issue, we propose AdaFlash framework, comprising two components: (i) an on-policy distillation (OPD) algorithm with reverse-KL divergence tailored for diffusion drafters, bringing stable convergence and effectively reducing domain-level variance; and (ii) an adaptive length head that dynamically adjusts the candidate sequence length on the fly, substantially lowering the verification cost of the target model and mitigating token-level variance. Experiments demonstrate that AdaFlash consistently improves speedup rate during deployment, with especially significant gains under high-concurrency, achieving up to 66% higher average throughput than previous SOTA. Our code is available at https://github.com/ZinYY/AdaFlash.

Yu-Yang Qian, Hao-Cong Wu, Chen Chen +4

State Key Laboratory for Novel Software Technology, Nanjing University · School of Artificial Intelligence, Nanjing University · Huawei Foundation Model Dept

Speculative Decoding for Diffusion Language Models Speculative Decoding LLM Inference Acceleration Diffusion Language Model Decoding On-Policy Distillation

Jul 21, 2026

Contrastive On-Policy Distillation

On-policy distillation (OPD) trains a student model on trajectories sampled from its own policy, providing dense token-level supervision by minimizing the divergence between the teacher's and student's output distributions at each token. Although existing OPD approaches effectively distill strong reasoning capabilities into student models, they inherently inherit uncurated chain-of-thought traces, exacerbating overthinking and reasoning redundancy. To address this limitation, we introduce COPD, a contrastive OPD framework. Specifically, for each token generated by the student, a frozen teacher evaluates the current student state under two contrasting prompts that induce low and high reasoning effort, respectively. The resulting difference in log-probabilities serves as a token-level advantage signal to guide the policy update. Rather than merely mimicking a single teacher distribution, COPD guides the student model toward acquiring concise and efficient reasoning strategies. We evaluate COPD across 9 multimodal benchmarks covering both reasoning and understanding tasks. Empirical results show that COPD substantially reduces reasoning length without hurting task performance, consistently improving efficiency across different tasks and model scales. In addition, this contrastive paradigm extends naturally to on-policy self-distillation (OPSD), establishing self-contrastive supervisory signals that enable a single model to compress its own reasoning without an external teacher.

Jiacheng Ruan, Jun Tang, Wenzhen Yuan +5

Shanghai Jiao Tong University · Alibaba Group

Language Model Distillation On-Policy Distillation Knowledge Distillation

Jul 21, 2026

MOPDA: Mixed-Trajectory On-Policy Distillation for Language-Guided Industrial Anomaly Detection

Large vision-language models (LVLMs) have shown strong potential for industrial anomaly detection (IAD) by providing image-level anomaly judgments and interpretable reasoning. However, reliably translating generated judgments into precise pixel-level localization remains challenging. We propose Mixed-Trajectory On-Policy Distillation for Language-Guided Industrial Anomaly Detection (MOPDA), the first framework to introduce on-policy self-distillation into LVLM-based IAD. For judgment learning, \method introduces Mixed-Trajectory Supervision, combining student-generated on-policy trajectories with evidence-conditioned teacher trajectories under a shared token-level distillation objective. Student trajectories preserve supervision on deployment-relevant response paths, while teacher trajectories provide complementary evidence-conditioned supervision. For dense localization, Language-guided Visual Anchoring uses the final judgment as a compact semantic condition to construct image-specific normal and abnormal anchors, which are contrasted with dense visual features to produce anomaly maps. This keeps language as semantic guidance while grounding pixel-level responses in visual evidence. Under a strict cross-dataset zero-shot protocol on five IAD benchmarks, \method outperforms the evaluated LVLM-based baselines on most detection, localization, and judgment metrics while remaining competitive with CLIP-based methods. Ablations further validate both mixed-trajectory supervision and final-judgment conditioning.

Shuimu Chen, Jing Jin, Nan Su +5

Tsinghua University · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) · Shenzhen University

Industrial Anomaly Detection VLM Distillation Multimodal Anomaly Detection On-Policy Distillation Zero-Shot Anomaly Detection Anomaly Detection

Jul 21, 2026

ABOPD: Antibody CDR Design via On-Policy Distillation

Antibodies are essential therapeutic molecules, and their complementarity-determining regions (CDRs) form the primary antigen-recognition interface. Recent protein generative models have demonstrated broad capabilities in biomolecular design, yet post-training strategies for downstream objectives remain limited. Standard denoising training operates on noisy states obtained by perturbing native structures, whereas recursive generation proceeds through model-generated intermediate states. For flexible antibody CDR loops such as CDR-H3, this mismatch can allow backbone deviations to accumulate along the denoising trajectory and compromise antigen-facing loop geometry. We introduce ABOPD, an antibody design framework based on on-policy distillation that leverages privileged native geometry during training to supervise states visited along the model's own denoising trajectories. With this fine-grained structural supervision, ABOPD substantially improves structural recovery on RAbD CDR-H3 generation, reducing RMSD by 0.42 Å (from 2.37 Å to 1.95 Å) and outperforming supervised fine-tuning and offline distillation controls, offering a path to higher-fidelity protein design.

Zhuo Yang, Jiaying He, Jiaqing Xie +5

Shanghai Innovation Institute · Southeast University · Zhejiang University +4

Diffusion Model Distillation On-Policy Distillation Protein Design

Jul 20, 2026

CriPO: Enhancing Rubric-based RL via Self-Distillation

Rubric-based Reinforcement Learning (RL) has recently shown promise in improving Large Language Models (LLMs) on open-ended tasks. A widely recognized limitation of rubric-based RL is limited exploration: criteria that no rollout manages to satisfy (Unexplored Criteria) receive no optimization signal. Recent methods address this by incorporating rubric information as external guidance during rollout generation, yet they introduce a train-inference mismatch: the policy is optimized on rollouts produced under external guidance while this guidance is absent at inference time, causing error accumulation through autoregressive decoding. Moreover, these exploration-focused approaches overlook a fundamentally different failure mode that we term Suppressed Criteria---criteria that are satisfied by some rollouts yet whose learning signals might be lost during optimization because scalar reward aggregation assigns them non-positive aggregate advantages. Our analysis reveals that suppressed criteria constitute a persistent and non-negligible failure mode---over 25% of samples exhibit this issue throughout training. To simultaneously address both unexplored and suppressed criteria without introducing training-inference mismatch, we propose Criterion-Distilled Policy Optimization (CriPO), which enhances rubric-based RL via on-policy self-distillation. For unexplored criteria, CriPO constructs a behavior-injection teacher and computes a filtered forward-KL loss to inject missing behaviors into the policy. For suppressed criteria, CriPO uses a counterfactual teacher to locate criterion-relevant tokens in negative-advantage rollouts, and corrects their advantages in GRPO to preserve useful patterns. Experiments on medicine and science benchmarks demonstrate that CriPO outperforms existing rubric-based RL methods, e.g., achieving an average gain of 3.3 points over GRPO on Qwen3-4B.

Mingxuan Xia, Yuhang Yang, Chao Ye +7

Zhejiang University · ByteDance

Credit Assignment in RL Rubric-Based RL On-Policy Distillation Rubric-Guided Generation Reward Design for RL

Jul 19, 2026

Distilled Reinforcement Learning for LLM Post-training

Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL) and on-policy distillation (OPD). However, RL relies on coarse-grained outcome supervision, resulting in difficult credit assignment and limited capability to acquire new knowledge. OPD, meanwhile, unconditionally matches teacher logits through KL divergence, which creates a dilemma: similar teachers provide little new knowledge, while substantially different teachers often yield ineffective guidance, largely restricting OPD to within-family distillation. We propose Distilled Reinforcement Learning (Distilled RL), which integrates teacher supervision into the RL objective to provide fine-grained guidance, selectively transfer new knowledge and avoid unconditional imitation. Distilled RL contains three components: reverse importance sampling with clipping, negative sample reset, and sequence-level geometric normalization. Through a concise and interpretable case study, we demonstrate that Distilled RL can effectively transfer previously unavailable knowledge from a teacher model to a student model. Extensive experiments across both within-family and cross-family distillation settings show that Distilled RL substantially outperforms standard RL and OPD in terms of both pass@1 and pass@k. Our code is available at https://github.com/597358816/Distilled-RL.

Chen Wang, Zhaochun Li, Jionghao Bai +4

College of Elite Engineers, Nankai University · Zhongguancun Academy · Beijing Institute of Technology +4

RL for Language Model Reasoning Cross-Architecture Knowledge Distillation On-Policy Distillation RL Post-Training Knowledge Distillation RL for Knowledge Distillation

Jul 18, 2026

CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation

On-policy knowledge distillation transfers reasoning from large teachers to compact students, but existing approaches suffer three compounding failure modes: (i) cold-start collapse, where a fresh student assigns near-zero mass to teacher-preferred tokens; (ii) state-agnostic divergence scheduling, where time-only forward/reverse-KL interpolation ignores the student's coverage state; and (iii) binary reward sparsity, where pass/fail signals discard information from partially correct traces. We present CADENCE, a unified framework with a targeted fix for each. Its DRIFT mechanism schedules a per-token convex mixture of forward-KL and reverse-KL surrogate objectives on student-sampled trajectories (per-token surrogates, not sequence-level KL gradient estimators). Six components extend it: (A) COVA, a coverage-adaptive

β

schedule accelerating the forward-to-reverse transition; (B) FTB, a forking-token boost concentrating gradient at high-entropy positions via a globally-normalized entropy reference; (C) CCD, a dense reward adding numerical-proximity partial credit for incorrect-but-close traces; (D) LAP, brevity-preferential correct-rollout reinforcement; (E) EMR, an entropy-matching calibration regularizer; (F) BSD, a bootstrapped self-distillation phase. On GSM8K and MATH-500 (corrected 512-token protocol, 5 seeds, reported std), CADENCE distills a 0.5B student from a 1.5B teacher to 69.8

\pm

0.5% GSM8K pass@1 (from 48.7% pretrained; 63.2% of the teacher gap closed) and to 72.1

\pm

0.4% with a 3B teacher (76.2% closed), beating the strongest matched-compute label-using baseline (DRIFT+binary reward) by +4.4

\pm

0.7 points. All experiments run on a single Apple Mac Studio (M-series, 64GB unified memory), showing principled distillation reaches strong reasoning quality without datacenter-scale hardware.

Satyam Kumar, Saurabh Jha

CoT Distillation On-Policy Distillation Knowledge Distillation

Jul 17, 2026

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning

Large reasoning models often solve problems through long chain-of-thought (CoT) traces, yet much of this computation is spent on redundant derivations, repeated self-verification, and detours that do not improve the final answer. Existing on-policy self-distillation methods reduce this cost by matching a student model to a concise copy of itself on prefixes sampled from the student's own rollouts. We show that this objective has an initialization bottleneck. Since supervision is applied only to visited prefixes, training from a verbose base model places the KL loss on contexts that are often noisy, redundant, or already off track. In such regions, a concise teacher can provide only local corrections, while the student continues to explore trajectories that an efficient reasoner should avoid. In this paper, we propose BIRD(Bootstrapped Iterative Self-Reasoning Distillation), a two-stage self-reasoning distillation method that improves the rollout distribution before on-policy training. BIRD first samples concise solutions from the base model under a brevity instruction, keeps only answer-correct traces, and performs a lightweight prompt-switch SFT step. The traces are generated with the brevity instruction but learned under the original task prompt, turning instruction-induced conciseness into a default reasoning behavior. Starting from this warm model, BIRD then applies on-policy reverse-KL distillation with a concise self-teacher, now on cleaner and more informative prefixes. Across Qwen3 series models, BIRD achieves a stronger accuracy-efficiency trade-off than prompting and cold-start on-policy distillation on MATH-500 and AIME benchmarks. On Qwen3-8B, it improves MATH-500 accuracy from 86.2% to 92.0% while reducing the average response length from 3,099 to 1,115 tokens. These results highlight prefix support as a central factor in efficient reasoning distillation.

Leichao Dong, Dongxu Zhang, Yiding Sun +4

1Xi’an Jiaotong University · 2Peking University

CoT Distillation Efficient Language Model Reasoning On-Policy Distillation LLM Reasoning

Jul 16, 2026

On-Policy Delta Distillation

On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervision from a teacher model. Although on-policy distillation has been studied and applied across various settings, its fundamental design remains underexplored. In this paper, we introduce a new distillation reward, termed the delta signal, instead of directly imitating the teacher's output distribution. The delta signal is defined as the difference between the teacher model and its base model prior to instruction tuning for reasoning capability. It therefore captures the changes induced by reasoning tuning and provides a more direct signal for transferring reasoning capabilities. Using extensive empirical evidence, we show that the delta signal substantially improves on-policy distillation and refer to the new distillation method as On-Policy Delta Distillation (OPD

^2

). Experiments across mathematics, science, and code-reasoning benchmarks demonstrate that OPD

^2

consistently outperforms conventional on-policy distillation, enabling reasoning LLMs to achieve strong performance with only a short post-training period. Code will be available at https://github.com/naver-ai/opd2

Byeongho Heo, Jaehui Hwang, Sangdoo Yun +1

NAVER AI Lab

RL for Language Model Reasoning Language Model Distillation On-Policy Distillation

Jul 16, 2026

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but its sparse trajectory-level rewards offer limited guidance on intermediate decisions, leaving a supervision gap between episode-level outcomes and token-level policy learning. We propose SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills and distills their behavioral effect back into the policy model. SEED first fine-tunes the policy to analyze completed trajectories and generate natural-language skills that capture reusable workflows, decisive observations, or failure-avoidance rules. During RL, the current policy both collects trajectories and serves as the analyzer that extracts hindsight skills from them. Policy updates therefore improve subsequent decision making and skill analysis together, allowing hindsight supervision to evolve with the policy. SEED then re-scores the sampled actions under ordinary and skill-augmented contexts, converting the skill-induced probability shift into a dense token-level on-policy distillation signal. This signal is jointly optimized with outcome-based RL, keeping the auxiliary supervision aligned with the current trajectory distribution. Extensive experiments on text-based and vision-based agentic tasks show that SEED consistently improves performance and sample efficiency, exhibiting robust generalization to unseen scenarios. Our code is available at https://github.com/jinyangwu/SEED.

Jinyang Wu, Shuo Yang, Zhengxi Lu +8

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

Agentic RL On-Policy Distillation Sparse-Reward RL RL for LLM Agents

Jul 15, 2026

Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape Pre-, Intra-, and Post-CoT Calibration

Large language models have made strong reasoning gains through supervised fine-tuning, reinforcement learning, and on-policy distillation, yet these post-training methods are usually evaluated only by final-answer accuracy. We study how they reshape confidence during reasoning. We introduce a three-stage calibration framework that evaluates confidence before, during, and after chain-of-thought generation, corresponding to difficulty estimation, early termination, and answer aggregation. Through a controlled comparison on mathematical reasoning benchmarks, we find that OPD provides the most useful pre-reasoning confidence, SFT gives the strongest online signal for early stopping, and RL produces the most reliable trace-level signal for aggregation. We further show that confidence reliability is position-dependent: RL confidence becomes informative after a path-commitment phase, while OPD confidence is useful early but can become inversely calibrated later. Based on this observation, we propose PosConf, a position-aware confidence strategy that uses confidence only from reliable relative-position intervals. PosConf improves RL answer aggregation by 6.1 points over majority voting and consistently improves OPD early stopping under tight token budgets, with gains up to 4.3 points by avoiding its later inverse-calibration region, showing that confidence in reasoning models should be used both stage-wise and position-awarely. Our code is available at https://github.com/EIT-NLP/Post-Training-Calibration.

Shuhao Li, Guodong Du, Anhao Zhao +3

Eastern Institute of Technology, Ningbo · The Hong Kong Polytechnic University

Confidence Estimation in Language Models Language Model Calibration On-Policy Distillation RL Post-Training LLM Post-Training LLM Reasoning

Jul 15, 2026

Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations

On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood. We present a systematic study examining the role, pathologies, and regulations of OPD. We first clarify the role of OPD as an exploration catalyst: it steers the student toward correct reasoning paths via dense token-level guidance, without expanding capability ceiling. We confirm this by showing that prompt diversity matters more than per-problem sampling numbers, and critically, that the effectiveness of OPD hinges entirely on the quality of its guiding signal. This dependency exposes two pathologies that derail exploration. The Student-Teacher Mismatch occurs when a large teacher-student distributional gap causes the guiding signal to misalign with task correctness, steering exploration in counterproductive directions. Length Exploitation arises when the aggregated token-level objective creates length-dependent shortcuts, allowing the student to game the reward landscape through response truncation or redundant padding, exploring degenerate length modes rather than reasoning strategies. To tame these pathologies, we investigate lightweight signal regulations: advantage clipping and log-scale compression, ensuring exploration is guided by faithful signals. Experiments across seven benchmarks demonstrate that these regulations alleviate length exploitation and enable effective distillation, stably surpassing OPD variants and RLVR baselines, thereby confirming that well-regulated signal quality, rather than mere teacher scale, governs successful exploration in OPD.

Rui Wang, Hongru Wang, Yi Chen +4

†The Chinese University of Hong Kong · ‡Tencent AI Lab

RL for Language Model Reasoning Language Model Distillation On-Policy Distillation Knowledge Distillation

Jul 14, 2026

ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation

Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compressed checkpoints can collapse on the free-form generation that deployment actually requires. Two observations trace this gap. First, greedy pass@

1

nearly vanishes after compression, yet pass@

k

recovers substantially under repeated sampling: useful generations are demoted, not erased. Second, the recoverable regime fails mainly through suffix repetition. Recovery should therefore train on the compressed model's own on-policy states with dense token-level supervision, which On-Policy Distillation (OPD) provides by reusing the pre-compression model as a frozen teacher. However, long on-policy rollouts spend early recovery budget on low-information repetitive suffixes, delaying loss descent. To mitigate this waste, we propose \shortopd, a short-to-long OPD schedule that detects teacher-confirmed repetitive suffixes, treats the surviving prefix as each rollout's effective length, and allocates future rollout budgets to the effective lengths the policy can currently use. Across math, code, and open-ended generation, \shortopd\ raises the compressed model's score to about

9\times

its unrecovered value and

1.6

--

4.4\times

standard recovery recipes (SFT w/o KD, KD, and SeqKD), and it matches a fixed

8192

-token rollout horizon within two points using a quarter of the training time (

8.5

vs.\

35.9

hours) and

71\%

fewer rollout tokens. We hope this recipe helps move structured pruning beyond marginal gains on perplexity and multiple-choice benchmarks, a step closer to deployment-ready generation quality.

Qingyu Zhang, Qianhao Yuan, Hongyu Lin +7

2Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences · University of Chinese Academy of Sciences · 1ByteDance

Open-Ended Generation LLM Pruning On-Policy Distillation Data Repetition in Language Model Training Text Generation