On-Policy Distillation

On-policy distillation instils multi-turn agentic reasoning through dense token-level supervision on the student's own trajectories, but a single domain saturates early, so further supervision has to be drawn from other domains. Multi-domain data mixing is the most direct way of incorporating them, at the cost of conflicts between their data distributions and of retraining the entire model whenever one domain is revised. Model merging avoids both by distilling every domain independently and fusing the resulting task vectors afterwards. We find instead that the benefit polarizes across domain pairs: on those exhibiting negative transfer, every merging operator we evaluate falls below the single-domain reference. We attribute this to cross-domain update coupling, where a substantial fraction of coordinates is updated comparably by both domains and a merge can therefore displace them by as much as their own updates. To overcome this limitation, we propose USA, which converts per-parameter update magnitudes measured during a brief warm-up into per-coordinate perturbation radii, reducing curvature precisely on the coordinates that carry most of the merging displacement. Experiments across mathematics, science and code at two student scales show USA strongest in all six transfer directions, ahead of the single-domain reference by more than four points on average, and reverse the negative transfer of the conflicting pairs.

On-policy distillation (OPD) trains a student on its own rollouts using dense supervision from a teacher. In multi-turn environments, a mistake at a critical decision step can redirect the subsequent rollout toward poor outcomes. We use low teacher confidence on student actions to select high-uncertainty steps for correction. In a controlled ALFWorld study, a single teacher correction at a low-confidence step improves subsequent student behavior and task success, motivating selective intervention during distillation. We propose UOPD, an uncertainty-aware intervention method for on-policy distillation. At low-uncertainty turns, UOPD executes student actions and applies the standard OPD loss. At high-uncertainty turns, it samples and executes teacher actions and trains the student to imitate them through supervised fine-tuning, which minimizes forward Kullback-Leibler divergence in expectation. UOPD utilizes adaptive uncertainty thresholds to target a scheduled intervention rate. Empirically, we evaluate UOPD across a broad range of agentic tasks, including ALFWorld, WebShop, and Search, demonstrating its superior performance over OPD methods and their variants. UOPD improves WebShop score by up to $15.8\%$ relative to standard OPD.

Large language models are increasingly expected to support diverse chemical reasoning capabilities within a unified model. One approach is to develop specialized capabilities separately and consolidate them through multi-teacher on-policy distillation, but this raises two questions: how should specialization be organized, and how should specialist guidance be integrated? We introduce ChemOPD, which addresses both. We estimate task affinities from supervised fine-tuning gradients and solve a constrained mixed-integer program(MIP) to construct partially overlapping specialist groups. During distillation, we retain a generalist teacher trained on all tasks so that specialist guidance supplements rather than replaces its supervision. Our anchor-residual objective gradually increases the routed specialist's contribution on student-generated responses. On ChemCoTBench, affinity-guided specialization produces task-dependent gains over the generalist teacher and improves several capabilities beyond semantic task grouping. Yet stronger teacher-side performance does not automatically yield stronger students: with the same specialists and routes, anchor-residual OPD improves most reported metrics over specialist-only distillation and realizes a larger share of the available teacher gains. These results highlight specialization and capability integration as connected but distinct design problems in chemical reasoning.

On-policy distillation (OPD) bridges teacher supervision and student behavior, but different teacher-student tokenizers introduce misalignment in both input tokenization (#1) and output logits (#2). Existing approaches address the former by matching same-text spans or converting tokens to bytes, often losing fine-grained token information or disrupting the native-token paradigm, while for the latter, strategies such as ranking, padding, or key-token selection retain only shared logit dimensions, resulting in much distribution loss. In this paper, we propose Dual-Vocabulary Language Model (DVLM), which replaces the teacher's LM head with a new student-vocabulary projection head and obtains full-dimensional student logits (for #2). To support student tokens (for #1), it takes a Parallel-Tokenized Sequence (PTS) as input, which concatenates the original teacher-tokenized sequence and a re-tokenized sequence formed by independently converting each student token into a teacher-token group. To avoid inference inconsistency with the original teacher tokens, the Hybrid-Prefix Attention (HPA) further restricts re-tokenized groups to their corresponding teacher prefix and uses its last state as the aggregation of the original student-token representation for projection into the student vocabulary space. Similarly, via the combined use of PTS and HPA, the DVLM teacher can provide distribution-aligned supervision with the student's input-tokenization and output-logit during OPD. Experimental results demonstrate that our DVLM teacher has a similar converged loss as the original teacher model and enables student models to improve performance across six reasoning tasks.

Since the advent of knowledge distillation, KL divergence has been the standard loss in distillation. Recently, on-policy distillation (OPD) has emerged as an efficient post-training paradigm for LLMs. As a distillation method, OPD naturally inherits KL divergence as its standard loss. However, in this work, we find that KL divergence may not be necessary for OPD. We show that simply preserving the update direction is sufficient for effective OPD. As long as the update direction is toward the teacher, OPD works. More precisely, it is not the direction of every token, but the direction of a small subset of tokens where the teacher and student disagree strongly. We first show that simply assigning a reward of (+1) to tokens where the teacher probability is higher than the student probability and (-1) where it is lower, which merely encourages updates toward the teacher, reproduces almost the same training mode as OPD with reverse KL. We further show that only the direction of a small subset of tokens with large teacher-student disagreement is critical, and training works as long as their update direction is toward the teacher, even if other tokens are pulled away from the teacher. And as an application of these findings, we introduce Consensus Multi-Teacher On-Policy Distillation (C-MOPD) to improve Multi-Teacher On-Policy Distillation (MOPD). Unlike MOPD, which routes each sample to a single teacher and may cause capability conflicts across domains, C-MOPD lets every sample be supervised by all teachers. Experiments show that C-MOPD consistently outperforms MOPD on both math and code benchmarks. Our code is available at https://github.com/LeapLabTHU/KL-Free-OPD.

On-policy distillation (OPD) trains a student on its own responses with token-level feedback from a stronger teacher, yet the teacher can fail on questions the student already answers correctly, and how often each model succeeds varies across tasks. OPD ignores these outcomes and, on average, pushes down even the student's correct responses; gating feedback by student correctness fixes the direction but uses the teacher in the same way whether or not it succeeded. We introduce DuoOPD, in which the student's outcome sets the direction of feedback and the joint teacher-student outcome decides how the teacher supports it: when only the teacher succeeds, its verified answer becomes context for scoring the student's failed response, and when only the student succeeds, a weight shared within the task reinforces the whole response. A single rule covers all four outcome combinations without task-specific settings. Across Qwen3 and Llama, DuoOPD outperforms all five baselines in mean macro accuracy, improving over OPD by 2.58 and 5.98 percentage points, and it also leads on two further task mixtures spanning scientific calculation, instruction following, and code generation. Ablations show that outcome-based direction alone stays near the gated baseline, while the joint-outcome designs supply most of the gain.

On-policy distillation (OPD) trains a student model on its own trajectories using dense token-level feedback from a stronger teacher model. Since each update is conditioned on the reasoning prefix already generated by the student, the prefix also shapes how effectively teacher feedback is converted into learning. We find that shared prefixes can lead to weak token-level updates, a phenomenon we call Prefix-Induced Supervision Attenuation (PISA). This attenuation arises in two common cases. (i) High student confidence can weaken corrective gradients even when the teacher disagrees. (ii) Tokens that rely on earlier reasoning can receive learning signals as weak as those for simple local continuations. To solve this problem, we propose Trajectory Dropout, a simple training-time intervention that exposes these weakened signals. The student first performs a standard full-context rollout to generate a complete trajectory. During training, we randomly drop a certain proportion of the student's reasoning trajectory, while the teacher continues to observe the complete trajectory for token-level supervision. This intervention strengthens corrections for overconfident predictions and introduces additional supervision at prefix-sensitive positions. Trajectory Dropout consistently improves average performance across teacher--student model pairs of different scales and six mathematical reasoning benchmarks, while also yielding gains on two out-of-domain benchmarks. It can also be flexibly integrated into existing OPD variants with negligible computational overhead, further improving their performance. These results demonstrate that Trajectory Dropout provides a simple mechanism for strengthening token-level supervision across model scales and OPD objectives.

On-policy distillation (OPD) transfers the capabilities of a large language model to a smaller student by providing teacher supervision on the student's own rollouts. In long-horizon agentic tasks, however, uniform token-level matching can allocate supervision poorly: a large local discrepancy need not improve future behavior, while consequential guidance may be beyond the current student's reach or fail to persist without privileged input. We formulate long-horizon OPD as hierarchical supervision allocation and argue that productive guidance lies at the intersection of future utility and current learnability. Crucially, this intersection evolves as the student learns. Based on this principle, we propose LENS-OPD, a coarse-to-fine framework that organizes supervision through Locate, Validate, and Refine. Locate adapts trajectory exposure to the student's evolving competence and proposes a candidate decision for intervention. Validate tests whether teacher guidance at that decision improves the same student's subsequent behavior. Refine internalizes the beneficial guided behavior into the deployable policy and concentrates token-level supervision on decisive teacher-student conflicts within the validated turn. These stages are nested: each finer allocation is conditioned on the coarser decision, rather than being optimized as an independent importance score. Experiments across multiple long-horizon agent benchmarks and student-teacher configurations show that LENS-OPD consistently improves task performance over vanilla OPD and strong curriculum- and selection-based baselines. Our results suggest that effective long-horizon distillation requires teaching at the right depth, the right decision, and the right token.

Reinforcement learning with verifiable rewards (RLVR) often relies on sparse outcome rewards, providing coarse supervision for long-horizon agents. On-policy self-distillation (OPSD) complements this signal with dense privileged feedback. However, we identify Decision--Timestamp Mismatch: privileged guidance may be misaligned with the student's functional decision because the corresponding decision can occur at a different timestep, while the student's decision itself may span multiple timesteps rather than being tied to a single timestamp. Thus, timestamp-local supervision can misalign both the context and the temporal scope of credit. To address this mismatch, we introduce AlignOPSD, following the principle of aligning supervision before assigning credit. Decision-Aligned Supervision Rectification re-scores the same student-sampled response in functionally matched contexts across sibling rollouts to calibrate local teacher evidence. Semi-Markov Hierarchical Credit Assignment then derives variable-duration decision spans from correspondence changes and uses rectified evidence to allocate outcome-grounded credit across spans and their constituent turns. We evaluate AlignOPSD with Qwen2.5-3B and Qwen2.5-7B on ALFWorld, WebShop, and Search-QA against representative baselines. AlignOPSD outperforms both GRPO and StepOPSD across all eight backbone--aggregate-metric comparisons, improving on GRPO by 5.5--8.7 % and ranking first in six. Additional analyzes examine the two alignment stages and hyperparameter sensitivity between tasks. Our code is avaliable at https://github.com/mingju-c/Align-OPSD

Diffusion large language models (dLLMs) generate text by iterative unmasking. At each denoising step, a dLLM proposes a token at every masked position, but the decoder commits only a confident subset of these proposals. Trace-based on-policy distillation (TOPD) builds on this process by matching the student to a stronger teacher, yet only at the committed positions. We argue that this discards much of the useful signal, which resides in the uncommitted proposals, where the student has made a prediction but is not yet confident enough to commit it. We call these proposals hesitations. In our pilot study on an SDAR-4B student, hesitations make up only 24% of supervisable state-position pairs but carry 66% of the teacher-student divergence. To exploit this signal, we propose Hesitation-Aware On-Policy Distillation (HOPD), which extends teacher distribution matching to every masked position of each denoising step. Because hesitations are not equally informative, we further allocate supervision using hindsight from the completed trajectory, placing more weight on positions whose proposal was later disagreed with the final token and on blocks where first-step proposals rarely survive. Since both models already produce distributions at all masked positions, HOPD requires no additional forward passes over TOPD. The only extra cost is evaluating the loss at more positions. With SDAR-1.7B and SDAR-4B students distilled from TraDo-8B-Instruct, HOPD achieves the best average score among the evaluated methods on five math and coding benchmarks, under both static and dynamic decoding and at both scales. It also speeds up decoding. On SDAR-4B, the HOPD student hesitates less and commits 11% more tokens per denoising step than TOPD, while reaching higher accuracy.

Recent advances in online policy self-distillation (OPSD) have demonstrated that large language models (LLMs) can improve their capabilities by leveraging external privileged information (PI), such as manual annotations or feedback from external environments. However, obtaining accurate annotations and constructing sophisticated environments often require substantial human effort and computation, limiting the scalability of OPSD. While a few recent studies have explored self-improvement without external PI, the resulting gains remain limited. In this work, we explore whether LLMs can achieve comparable self-improvement without external PI. Our key observation is that a single LLM can support multiple reasoning modes, such as deep-thinking and non-thinking modes, with deep thinking generating additional information during reasoning. Based on this observation, we propose Self-Evolving Online Policy Distillation (SeOPD), which enables LLMs to distill and internalize information generated by their own chain of thought (CoT). Specifically, it (1) generates CoT with the deep-thinking mode, (2) produces responses with the non-thinking mode, and (3) uses the generated CoT as PI to provide token-level supervision for the non-thinking response, allowing new information inferred during reasoning to guide the non-thinking mode and be internalized into the shared model parameters, thereby improving both non-thinking and deep-thinking capabilities. Extensive experiments across LLMs and tasks demonstrate the effectiveness of SeOPD.

On-policy distillation (OPD) trains a student to match a teacher's next-token distributions on student-generated trajectories. However, privileged information supplied to the teacher for OPD training may contain sensitive data. Whether the student leaks private information about the records supplied to the teacher during distillation remains poorly understood. To the best of our knowledge, we present the first systematic study of membership inference in this setting. We find that fresh student trajectories expose sparse membership signals that fixed reference-answer losses often miss. These signals are mixed with probability changes caused by training on other records. We introduce Leaky, which samples fresh trajectories from the target model and compares its token log-probabilities with the maximum across matched reference models trained without the candidate records. It applies Leaky ReLU to the resulting gaps, preserving positive gaps and downweighting negative gaps as an approximate correction for incidental positive gaps in non-members. Across fifteen targets spanning mathematics, medical question answering, and code generation, Leaky outperforms all evaluated baselines and achieves mean AUROC 0.875, compared with 0.614 for the strongest baseline on each target in the main evaluation. On the same sampled trajectories, the strongest baseline achieves mean AUROC 0.826. These results show that students trained through OPD can expose the membership of records used for teacher supervision, even when fixed reference-answer losses provide little evidence of membership.

Diffusion vision-language models generate answers by gradually resolving masked tokens, making accurate conditional prediction in partially resolved states central to post-training. Masking completed answers yields coherent contexts and targets, but prescribed masks do not reflect the model's reveal decisions. Its trajectories capture these decisions, yet their provisional visible tokens can conflict with the target response. Outcome-based reinforcement learning follows these trajectories but provides only response-level feedback, which loses contrast when sampled rewards tie. To align coherent token-level supervision with the model's reveal decisions, we introduce Counterfactual Trace On-Policy Distillation (CT-OPD), which combines completed teacher responses with trajectory masks from the current student. CT-OPD retokenizes each teacher response in the student's vocabulary and extracts unresolved-position masks at successive stages of the student's reverse process. For each mask, it discards provisional rollout values and reconstructs the partial state from the teacher endpoint, so the supervised positions follow the current trajectory while the visible context and targets remain consistent with the same response. The student is trained on these reconstructed states with its native categorical loss, and trajectories are refreshed as the model evolves. Across dense and sparse diffusion architectures, CT-OPD consistently enhances multimodal understanding and reasoning capabilities, with gains of up to 9.80 points on the nine-benchmark average. On the unified understanding-and-generation architecture, it also improves both visual understanding and image generation, showing that the same principle transfers across architectures and modalities. Ablations further attribute these gains to coherent reconstruction and current-model trajectory masks.

Reinforcement learning (RL) can induce substantial reasoning capabilities in large language models (LLMs), but how much of this capability transfers across model scales, and how quickly, remains unclear. We study the scaling properties of on-policy distillation (OPD) across weak-to-strong, same-base, and strong-to-weak teacher--student setups. We find that early OPD training dynamics uniformly exhibit a regular useful-transfer regime, in which held-out accuracy (the gold score, $G$) rises approximately linearly in $d=\sqrt{\mathrm{KL}(π_θ\Vert π_{\mathrm{ref}})}$, the square root of token-level reverse KL divergence from the student initialization. In every observed weak-to-strong pair, the student's peak gold score exceeds its teacher's own, so a compact RL expert can transfer capability to a much larger student via OPD. To estimate OPD outcomes, we fit power laws for how $G_{\mathrm{peak}}$ and the slope of the useful-transfer regime scale with student and teacher parameter counts and with teacher gold score. These laws show that peak gold score improves with teacher scale only up to roughly the student's scale, and that at a matched gold score smaller teachers transfer better, so a teacher's score alone does not define its supervision value. We also study the scaling effects of two OPD variants, bootstrapping weak-to-strong OPD, and the degree of on-policy supervision.

On-policy self-distillation densifies agent training without external teachers: a policy conditioned on privileged hindsight provides step-level guidance for its own unprivileged rollouts. For search agents, however, hindsight can make the teacher prefer a query that does not improve retrieval from the student's state. Existing methods either distill this preference directly or filter it with model-internal scores, but neither strategy verifies the query's executed retrieval consequence. We propose Information-Gain-Gated Self-Distillation (IGSD), which verifies on-policy token proposals with environment feedback before distilling them. Treating each query token as a micro-action, IGSD completes the teacher's token proposal and the student's sampled token into matched queries and executes both from the same failed state with the same retriever. Shared counterfactual controls account for query-conditioned shifts in answer likelihood, so their difference, the executed paired information gain, provides a relative utility contrast for the retrieved documents. IGSD uses this contrast as a positive-only soft weight for candidate-pair distillation, while leaving the GRPO objective unchanged and confining verification to training. Across seven single-hop and multi-hop QA benchmarks, IGSD reaches macro-average exact-match accuracies of 42.8% and 47.0% with 3B and 7B policies, respectively, without inference-time verification. These results support environment-verified hindsight as an effective approach to reliable action-level supervision for search agents.

On-policy reasoning models can learn from task rewards or teacher signals, but these sources differ in form and can favor conflicting updates, leaving unclear which should guide a given reasoning action. We introduce Expected Reasoning-Step Return (ERSR), which treats semantic reasoning steps as macro-actions and uses Monte Carlo student-policy rollouts to estimate the expected final task reward of student-generated and teacher-proposed actions in a common return space for step-level comparison. ERSR analysis reveals an outcome-dependent asymmetry: student actions are more beneficial than teacher replacements on successful trajectories, whereas teacher replacements become more beneficial on failed trajectories. We further show that student answer-probe gains track student-step ERSR utility and distinguish beneficial from harmful reasoning steps. Based on these findings, we propose \textbf{Return-Referenced On-Policy Learning (R$^2$OPL)}, which reinforces student reasoning on successful trajectories and distills teacher signals on failed ones, while using group success rate for difficulty scaling and student-probe gains for step-level modulation. Experiments across reasoning benchmarks and teacher--student configurations show that R$^2$OPL consistently outperforms strong baselines. ERSR training dynamics further show that R$^2$OPL jointly exploits substantial utility from both reward- and teacher-side signals, whereas existing hybrids often leave substantial residual utility in one branch.

On-policy distillation (OPD) is a promising approach to language-model adaptation, aligning teacher supervision with the student's own generated trajectories. When adaptation prompts are distributed across clients, can this process benefit from federated collaboration? We study federated OPD and find that substantial collaboration gains can be obscured by learning-rate sensitivity: FedAvg can perform no better than independent local training at a small learning rate, yet recover a clear advantage at a larger rate. We explain this phenomenon through the student's dual role as learner and generator of future training data. An aggregation-induced optimization lag can delay access to useful teacher supervision, which in turn slows subsequent learning. Our theory establishes this aggregation--rollout feedback in a solvable model with a common optimum and stable updates, and identifies two coupled roles of learning rate: learning from current supervision and reaching future supervision. Guided by this analysis, we propose FedTOPS (Federated Teacher-guided On-Policy Scaling), which reuses teacher feedback on current trajectories to adapt the FedAvg update magnitude under clientwise predictive-change constraints. Across six mathematical reasoning benchmarks, FedTOPS improves macro Avg@8 over FedAvg by 4.56--14.57 percentage points across the evaluated student models and local learning rates.

Code-as-Policy agents accomplish long-horizon embodied tasks by generating and executing code, yet continually improving them with teachers that are stronger but not globally reliable remains a key challenge. Existing distillation methods typically treat the teacher's complete behavior as the supervision target and thus misassign training credit on states where the teacher fails. We propose RE-0, a recursively verified policy improvement framework: rather than assuming that the teacher globally outperforms the student, RE-0 requests local corrections from the teacher on the student's own failure histories and checks in the environment whether each correction is genuinely beneficial; verified corrections yield immediate improvement. Building on this, we propose RE-OPD, which turns verified interventions into supervision for on-policy distillation. Only counterfactually verified teacher interventions provide distribution-level supervision, weighted by their measured local benefit, and the improvement they induce is projected back into the standalone student, so both where supervision is applied and how much credit the teacher receives co-evolve with the student policy. We further prove that the student's per-round gain is lower-bounded by its verified intervention gain up to verification and projection error terms. Experiments across multiple Code-as-Policy embodied tasks show that RE-0 improves both teacher-assisted execution and the standalone student, and generalizes to novel robots and scenes.

Visual token reduction is an effective way to accelerate multimodal large language models (MLLMs), but performance deteriorates rapidly under extremely low token budgets. Existing work has explored both visual-token selection and training-based adaptation to reduced visual inputs. We take a step further by asking how a heavily compressed MLLM should learn from the states induced by its own generations. This setting naturally calls for on-policy self-distillation: a heavily compressed model is supervised on the states induced by its own generations, while its full-token counterpart serves as an information-rich teacher. Based on this insight, we propose LT-OPD, a training framework for extreme visual-token reduction. The student rolls out responses with only a small fraction of visual tokens, and a frozen full-token copy of the same MLLM provides distributional supervision along these student-generated trajectories. To stabilize on-policy learning when visual evidence is severely limited, we further introduce a budget-level curriculum that progressively decreases the token budget during training. Across nine benchmarks on Qwen3.5-4B, LT-OPD raises average retained performance under 5% visual-token retention from 68.6% to 82.3%, outperforming training-free, training-based, and reinforcement-learning baselines at the same budget. The gains transfer consistently to Qwen3.5-9B, GLM-4.6V-9B, and LLaVA-OV-1.5-4B. LT-OPD also reduces KV-cache usage by 85.2% and prefill FLOPs by 85.4% without additional inference overhead, demonstrating that on-policy learning can substantially recover capabilities lost to extreme visual-token reduction.

Regional-to-global distillation uses crop-conditioned guidance to improve full-image understanding. The challenge is to effectively transfer the teacher's crop-based advantage to the student's full-image inference. We propose progressive-view on-policy distillation (PVD), which shifts the student's view distribution from the crop toward the full image through an intermediate aspect-preserving padded crop. The padded crop preserves regional content while matching the full image's visual-token grid. Across stages, the view mixture assigns increasing probability to the full image. A lightweight regional-advantage weighting reallocates token-level supervision using the crop-conditioned teacher-student log-probability gap. Evaluated under each sampled input, it applies mild reweighting when the gap is small and emphasizes higher-gap tokens when the gap widens. A Jensen-Shannon metric decomposition interprets this schedule as a shift from matched-input imitation toward the deployment objective. Across benchmarks spanning perception, visual mathematics and general multimodal question answering, PVD-full reaches an average accuracy of 77.51 over three seeds, improving on the reward-free distillation baseline by 2.01 points and on its reward-matched variant by 1.00 point. In the reward-free setting, PVD-distill still gains 1.16 points.

Domain experts trained from a shared checkpoint can transfer their specialized capabilities to a single student through on-policy distillation (OPD). Existing research primarily focuses on improving this merging process, while the algorithms used to train the experts have received limited systematic comparison. We investigate which training algorithm produces teachers better suited to OPD through controlled single-teacher comparisons of supervised fine-tuning (SFT) and reinforcement learning (RL) across Agentic, Reasoning, and Perception. We further examine whether this advantage extends to multi-teacher OPD (MOPD). Teachers and students share the same Qwen3.5-9B initialization, and the two teacher types are compared at similar task performance. Our single-teacher experiments show that RL teachers yield stronger students and higher recovery of teacher performance gains across all three domains. In MOPD, the RL teacher group also yields a student with a higher three-domain mean score and higher overall teacher gain recovery than the SFT teacher group. Our further analysis shows that RL teachers undergo smaller parameter displacements from the shared initialization than SFT teachers. Teacher--student Top-K overlap also increases faster early in OPD or remains consistently higher with RL teachers than with SFT teachers. These findings support the hypothesis that RL teachers' smaller departures from the student's starting point facilitate learning through OPD, resulting in stronger students.

On-Policy Context Distillation (OPCD) has recently emerged as a powerful technique for transferring context to student models and for self-improvement. In OPCD, the teacher is conditioned on privileged information, and the goal is to minimize the Kullback-Leibler (KL) divergence between the privileged teacher and the student, evaluated on student-generated tokens. Many existing studies show that using instance-specific gold answers or gold demonstrations as the default privilege can hurt training performance, especially out-of-distribution (OOD). In this work, we instead design general instructions that target common student mistakes observed on the training samples, and show that such simple instructions can outperform gold as the OPCD privilege. In autoformalization tasks, using a matched formatting instruction as the privilege could outperform gold in OOD accuracy by a large margin. In 7 out of 8 experiments using ProverQA, ProofWriter, and ProntoQA as datasets, and Qwen3-Thinking and Olmo3-Thinking families as models, matched instruction privileges outperform gold in OOD by 4 to 17 points, while remaining on par with gold in-domain. Each instruction is only a few sentences (and thus contains much less information compared to all instance-specific gold) and is applied uniformly to every training sample. These results indicate that a general instruction, which applies equally to source and target domain examples, can be substantially more transferable than instance-specific gold in OPCD while maintaining in-domain performance.

Hybrid transformer architectures that replace most softmax attention layers with linear attention offer transformer-level quality at a fraction of the memory cost. Rather than pretraining such models, a growing body of work distills them from already trained full-attention transformers. However, these distilled models often collapse on long-context retrieval and reasoning tasks, particularly when operating in thinking mode, where the efficiency gains of hybrid architectures matter most. Since linear attention layers must compress context into a fixed-size state, their errors compound over long sequences. As off-policy distillation never teaches the student model to recover from this drift, tasks that necessitate longer sequence lengths become especially challenging. We introduce On-Policy Attention Linearization (OPAL) in which the hybrid attention student samples its own long-context trajectories and receives dense supervision from the frozen full-attention teacher. Applying OPAL to Qwen3-4B and MiMo-7B-RL-0530, we recover $87$--$94\%$ of full-attention performance on commonsense reasoning, $100\%$ on needle-in-a-haystack (NIAH) retrieval, and $83$--$93\%$ on mathematical reasoning with only 3B training tokens. We achieve these results without supervised fine-tuning (SFT) or reinforcement learning with verifiable rewards (RLVR). Compared with the strongest prior linearization method, which recovers $68\%$ of its teacher's retrieval performance and $21.6\%$ absolute average mathematical reasoning accuracy, OPAL fully recovers retrieval and achieves $67.6$--$72.2\%$ on math reasoning.

Modern LLM post-training composes supervised fine-tuning (SFT), reinforcement learning with verifiable rewards (RLVR), and on-policy distillation (OPD) into multi-stage pipelines, yet these stages are typically designed and evaluated in isolation. We show that this composition is consequential: a stage that improves the current model can make the next stage less effective. Through controlled experiments with Qwen3 models on math and science reasoning, we first characterize OPD across nine student-teacher pairs spanning 2x to 53x parameter ratios and show that OPD effectiveness depends on student-teacher compatibility rather than teacher scale alone. The surrounding stages of OPD reshape this compatibility in three ways: (1) A brief SFT warm-up improves subsequent OPD, while an RLVR-strengthened student regresses under distillation from the same teacher. (2) Adapting the teacher with RLVR raises downstream OPD accuracy in proportion to the capability it adds. Following these two interventions, we find that combining teacher adaptation and student warm-up alone raise average OPD accuracy from 29.2% to 43.8% (50% relative improvement) after the same number of distillation steps, with additional preparatory training. (3) At comparable accuracy, OPD leaves a stronger initialization for downstream RLVR than SFT, with a gap that widens as RL compute scales. Our results suggest that each post-training stage should be chosen not only for the capability it adds, but for the learning interface it creates for the next stage.

Black-box On-Policy Distillation (OPD) seeks to improve a student from its own generations when the teacher provides sampled responses but not token probabilities. Adversarial distillation offers one route: it learns a discriminator over prompt-matched teacher and student responses and uses its score as the policy reward. However, sampling discriminator negatives from the latest student at each step couples the learned reward to a negative distribution that changes after every policy update. We address this moving-target problem with persistent-negative adversarial distillation, a live-pool method that replaces a fraction of each discriminator batch with historical, prompt-matched teacher--student comparisons. Under matched discriminator compute, historical comparisons train the discriminator, while GRPO remains on-policy with fresh student responses. Our analysis identifies the Bayes-optimal reward as a teacher-to-negative log-density ratio and, under explicit assumptions, shows how persistent negatives anchor the discriminator and reduce reward-estimation MSE relative to fresh-negative training. Across two student families, three judges, and four judged-chat benchmarks, persistent-negative adversarial distillation consistently improves performance over current methods at matched discriminator compute. It also yields smoother fresh-policy discriminator trajectories, with fewer below-chance dips. These findings identify the discriminator's negative distribution as an important design axis in black-box on-policy distillation.

Multi-teacher on-policy distillation (MOPD) integrates specialized capabilities into a single student, but existing practice typically hard-routes each prompt to a domain-matched teacher for the entire rollout. This dependence on prompt-level domain labels restricts using unlabeled training mixtures and leaves complementary signals from other teachers unused. We introduce MOPD-Router, a framework that routes supervision over the full teacher pool at each token, without domain labels or training a separate routing model. Its plug-in interface supports different metrics for selecting and weighting teacher-specific OPD signals. Within this interface, we propose ExpertAlign, which scores each teacher by whether its correction to the student at the current token expresses the specialization that teacher acquired during post-training, and compare it against two reference metrics built on teacher confidence (Entropy) and teacher-student discrepancy (Novelty). Experiments on unlabeled and domain-labeled training mixtures under strong-to-weak and same-size distillation scenarios show that ExpertAlign achieves the strongest overall performance in all four settings. On unlabeled data, it improves the overall score by 5.88 (+12.3%) points over Mean aggregation; on domain-labeled data, it outperforms standard MOPD by 3.95 (+7.8%) points without using available domain labels. These results demonstrate token-level routing can exploit cross-domain complementary supervision, and reduce exclusive reliance on prompt-level domain assignment. Code is available at: https://github.com/TURLEing/MOPD-Router.

Speech Language Models (SLMs) inherit strong instruction-following capabilities from pretrained language models, yet ASR specialization can substantially degrade them. To address this ASR--QA trade-off, we propose Task-Specific On-Policy Distillation (TS-OPD), which leverages models before and after ASR specialization as complementary QA and ASR teachers. The student generates separate task-conditioned trajectories for ASR and QA, each supervised only by its corresponding teacher, thereby reducing direct competition between the two supervision signals. Experiments on basic ASR, contextual ASR, and QA demonstrate that TS-OPD improves recognition while preserving QA capability. Moreover, TS-OPD remains robust across different balancing coefficients and continues to benefit from increased distillation data.

Direct On-Policy Distillation (Direct-OPD) transfers reinforcement-learning-induced policy improvements from a small model to a larger student by using the token-level log-ratio between post-RL and pre-RL checkpoints as dense supervision on the student's own rollouts. This transfer rewards the policy shift at every state, yet the log-ratio measures only relative change: it can stay fixed even as the probability mass that both checkpoints assign to the student's candidate tokens vanishes. Through an exact construction, we show that the Direct-OPD reward and its update can remain unchanged while the Jensen-Shannon divergence (JSD) and both KL directions between the checkpoints vanish with this mass, and we note that a small JSD bounds how much the teacher's behavior changed. Motivated by this analysis, we propose Selective Supervision for Direct-OPD (S$^2$D-OPD), which ranks student-sampled states by their teacher-reference JSD and masks Direct-OPD supervision at low-divergence states, retaining only the top 10% of states per response. Across two teacher pairs and four student models ranging from 1.7B to 8B parameters, S$^2$D-OPD improves held-out accuracy over dense Direct-OPD on AIME and HMMT benchmarks in seven of eight settings and matches it in the eighth, without extra forward passes.

On-policy distillation (OPD) corrects a student on the responses it writes, but its signal is the teacher's next-token distribution: it tells the student what the teacher says but misses how it thinks. Latent supervision promises the missing part by aligning the student's latent states to the teacher's. Recent methods such as OPRD bring this signal into on-policy distillation. However, we observe two failures of this recipe when distilling Qwen3-4B and Qwen3-8B into Qwen3-1.7B-Base. Early gain, late collapse: latent supervision alone lifts MATH-500 accuracy from 25 to 46 in 10 steps, but subsequent training degrades performance down to 11 with no recovery. Better alignment, worse behavior: although the alignment metric steadily improves throughout this collapse, the most aligned model turns out to be the worst performing. Further analysis suggests a mismatch in how the latent signal is applied: layers paired by depth play different roles in the two models, so continued alignment may pull the student toward teacher states it cannot understand. To address this, we propose LastOPD, which applies the latent signal only at the last-layer state, the common interface both LM heads read, and only during a 10-step crossfade into token-level OPD. This keeps the useful part of the latent signal and hands the student to token-level supervision before the collapse sets in. Extensive experiments show that LastOPD improves MATH-500 over token-only OPD by 5.55 and 4.02 points with the 4B and 8B teachers, leads on most held-out datasets, and reaches the final score of token-only OPD in about half the steps. Code is available at https://github.com/Muyiiiii/LastOPD.

Audio-language models (ALMs) can exploit textual shortcuts to answer questions while overlooking acoustic evidence, weakening audio understanding. On-policy distillation (OPD) trains compact ALMs by supervising student-generated responses with teacher predictions, but does not explicitly distinguish acoustic support from linguistic predictability. We propose Reward-Tilted On-Policy Distillation (RT-OPD) to strengthen acoustic grounding. Given the same question and student-generated text, a frozen teacher predicts the next token with and without audio inputs. Their log-probability contrast defines a reward that reshapes the teacher distribution for reverse-KL distillation, emphasizing the additional evidence provided by audio. Across two compact students and three benchmarks, RT-OPD consistently outperforms Vanilla OPD. Experiments with silenced and replacement audio further suggest that RT-OPD strengthens the student's reliance on acoustic evidence. Our 3B model achieves 72.72% accuracy on MMAU, the highest among the compared 3B models and competitive with several 7B and 8B models. Code and model checkpoints are available at https://github.com/KaiyangLi1992/RT-OPD.