Overview

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

Latest papers

557 papers70 papers in the last four weeks, down 63% on the four weeks before. 0.5% of all new papers.

Oct 8, 2026

Policy Alignment: New Signals for Membership Auditing in On-Policy Distillation

On-policy distillation (OPD) trains a student model by aligning its policy with a teacher model on trajectories generated by the student model itself. Through this process, the student policy moves toward the teacher on the prompts used for distillation. However, these prompts are often private and costly, creating a need for prompt-level membership auditing. Existing methods mainly rely on likelihood-based confidence signals or student policy drift between checkpoints, but they do not capture the teacher-induced direction of the student update. In this paper, we propose Policy Alignment Membership Auditing (PAMA), a new auditing framework tailored for OPD. Our key observation is that a member prompt directly contributes to the teacher-guided policy update, while a non-member prompt only experiences indirect effects through cross-prompt generalization. Based on this directional trace, PAMA measures whether the student update moves toward reducing the teacher loss on a candidate prompt. Specifically, we introduce Teacher Alignment Gain (TAG) to estimate the teacher-aligned update direction from model outputs, and further combine it with student drift and uncertainty alignment signals for reliable membership auditing. We evaluate PAMA on six datasets and three teacher-student model families. On MATH, the primary evaluation benchmark, PAMA achieves AUC values of 0.791--0.941, improving AUC by 14.6--20.6% over state-of-the-art baselines.
Oct 8, 2026

SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces

Spatial coding agents significantly improve spatial reasoning in Multimodal Large Language Models (MLLMs) by using external tools to generate verified execution traces. However, this paradigm inherently suffers from prohibitive inference-time overhead and external dependencies. In this paper, we explore whether an MLLM can internalize this agentic capability to operate entirely tool-free. We begin with a simple observation: prompting an MLLM with summarized execution traces of a spatial coding agent naturally unlocks the model's internal spatial Chain-of-Thought (CoT). Motivated by this, we introduce SpatialOPSD, an on-policy self-distillation framework that internalizes spatial reasoning into a standalone MLLM by formulating verified agent traces as privileged information. To mitigate privileged-information leakage during distillation, we introduce Repetition-Aware Distillation, which combines repetition masking with unlikelihood regularization. Experiments across multiple benchmarks demonstrate that self-distilling SpatialOPSD achieves higher average accuracy than SFT and GRPO on both spatial and OOD datasets, exhibiting superior performance and generalization.
Oct 8, 2026

ReCal: Calibrating Structured Pruning for On-Policy Distillation Recovery

Structured pruning reduces the deployment cost of reasoning language models, but the resulting capability degradation can hinder subsequent on-policy distillation (OPD) recovery. Because OPD relies on student-generated trajectories, pruning damage that persists after offline distillation can limit its effectiveness. We propose RECAL, Recovery-Aware Calibration, a simple plug-and-play approach that improves OPD recovery by adjusting calibration before pruning. RECAL uses forward KL between an unpruned teacher and a pruned probe to identify teacher-supported predictions disrupted by pruning, then reweights calibration statistics to guide existing pruning criteria toward preserving these predictions. Across multiple models and pruning methods, RECAL consistently improves mathematical reasoning after OPD, achieving gains of up to 16.7 percentage points on AIME, alongside improvements in most code-generation comparisons. Further analysis shows that RECAL reduces residual damage at heavily affected tokens and establishes performance advantages that persist through recovery. These results demonstrate the value of recovery-aware calibration for improving on-policy distillation recovery of pruned reasoning models.
Oct 8, 2026

When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better

On-policy distillation (OPD) has become increasingly popular for transferring teacher capabilities to student models. In this work, we ask a critical research question: Is on-policy sampling always beneficial for distilling arbitrary teacher-student pairs? We show that a simple alternative, Semi-OPD, which distills from offline rollouts generated by the initial student, can often outperform OPD in both accuracy and training efficiency. Across 17 teacher-student pairs ranging from 1.5B to 235B parameters, Semi-OPD outperforms OPD in 14 cases, with up to +13.6% accuracy and 11.4x training speedup. We further find that the choice between OPD and Semi-OPD depends on the alignment between the initial teacher and student, quantified by an output-token overlap ratio: OPD is beneficial only when the two are highly aligned with high overlap ratios. Our deeper investigation suggests that effective distillation requires on-policyness w.r.t. both the student and the teacher. For misaligned pairs, student rollouts can become increasingly off-policy w.r.t. the teacher as context length grows, weakening the distillation signal. In contrast, Semi-OPD is often more stable, as it distills on shorter contexts while covering full trajectories and exposing the student to more teacher-preferred tokens. Beyond proposing Semi-OPD as an efficient alternative, our work motivates the community to rethink when to use OPD and to study stronger OPD variants with meaningful teacher-student pairs.
Oct 8, 2026

Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals

On-policy distillation (OPD) enables effective capability transfer between language models, yet the mechanisms underlying its failures are not fully understood. Across code generation and mathematical reasoning, OPD with larger-scale teachers exhibits early loss plateaus, with an average final loss reduction of 25.1% after 200 updates, compared with 96.2% for self-RL teachers, obtained by further reinforcement learning (RL) training of the initial student. To understand this difference, we analyze OPD as an idealized continuous-time dynamical system in the small-learning-rate limit. Our training-log diagnostics associate these plateaus with an early decline in a gradient-based learning-signal proxy while substantial loss remains; these measurements do not establish why the underlying gradient weakens. We further prove a local recovery guarantee for teachers sufficiently close to the initial student in a shared parameterization under regularity conditions, offering a conditional explanation for the success of self-RL teachers in our experiments. Across runs with and without loss plateaus, we observe small relative parameter changes (0.025-0.098%) and high similarity between the student's representations before and after OPD (linear CKA >0.98>0.98 across layers). These observations suggest that limited representation adaptation may contribute to learning-signal collapse, a hypothesis that remains to be tested. Code is available at https://github.com/leizhao7/opd-learning-signals.
Oct 8, 2026

PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation

Vertical-domain few-shot classification remains challenging for small language models, as limited supervision makes it difficult to acquire domain-specific decision knowledge. On-Policy Distillation (OPD) can improve teacher-guided adaptation by supervising student-generated rollouts, while GRPO-based reinforcement learning can further refine downstream predictions. However, existing KD-to-RL pipelines typically rely on globally fixed transition schedules, ignoring that different samples may require different amounts of teacher-guided acquisition before reward-driven refinement. We propose PIVOT (Perplexity-Informed Transition Optimization), a dynamic transition framework that routes samples between OPD and GRPO according to teacher-evaluated sequence perplexity. PIVOT moves low-perplexity samples to GRPO for reward-driven refinement while keeping high-perplexity samples under OPD for continued domain knowledge acquisition. Experiments on Banking77 and HWU64 show that PIVOT consistently outperforms continued OPD and globally synchronized OPD→\rightarrowGRPO baselines under the same number of post-warm-up student optimization steps, achieving stronger downstream performance and more stable training dynamics.
Oct 7, 2026

Stochastic Teacher Intervention for Agentic On-Policy Distillation

On-policy distillation (OPD) efficiently transfers capabilities from a stronger teacher to a student language model through dense token-level supervision on student-generated rollouts and has shown promise on complex tasks such as mathematical reasoning. However, in multi-turn agentic tasks, student decisions shape subsequent observations, causing early errors to accumulate across turns. The resulting trajectories can drift away from the teacher's rollout distribution, making the teacher's token-level supervision less reliable or even counterproductive for OPD training. To address this issue, we introduce STI-OPD, a stochastic teacher intervention framework for multi-turn agentic OPD. During multi-turn interaction, STI-OPD uses teacher intervention guided by teacher-student policy discrepancy to replace the student's proposed action with a teacher-generated one to maximize the acquisition of reliable supervision. We further develop a stochastic intervention strategy, addressing the limitations of previous threshold-based or fixed-schedule approaches, that estimates policy discrepancy using KL divergence and maps it to an intervention probability. By sampling whether to intervene from this probability, STI-OPD adaptively balances teacher control with student exploration. To learn from the resulting mixed-policy trajectories, we introduce an Importance-Weighted Reverse KL objective that corrects the token sampling mismatch between teacher-generated responses and the student policy to preserve the original OPD objective. Across tool-integrated reasoning and long-horizon interaction, STI-OPD outperforms the strongest prior OPD baseline on every evaluated benchmark and student size. Ablations further show that both discrepancy-guided intervention and importance weighting contribute to these gains.
Oct 7, 2026

Composing What Each Teacher Learned: Delta Distillation for Multi-Teacher On-Policy Learning

Multi-teacher on-policy distillation (MOPD) is used in two settings. In common-domain composition, several teachers score each student rollout from one prompt domain and their signals form a single target; in routed-domain distillation, prompts from different domains are assigned to the corresponding specialist. Both settings usually transfer each teacher's endpoint policy, which mixes what post-training changed with preferences inherited from the teacher's base. We introduce ΔΔ-MOPD, which transfers each teacher's teacher-minus-base logit shift re-anchored at the student's frozen initialization, and compare it with endpoint supervision in both settings while holding teacher selection fixed. We first expose the mechanism that impedes endpoint transfer: inherited base pull can exceed the post-training shift. Removing it reduces the teacher-term norm ratio and target--student KL. Across our experiments, the results suggest that shift targets are particularly useful when teacher signals are combined at a state. With three composed teachers, ΔΔ-MOPD exceeds endpoint composition by 4.114.11 Math and 1.951.95 five-benchmark points; with two, it matches endpoint accuracy. Under phased routing, it achieves higher mean performance in both phase orders and reduces the observed order gap from 10.5010.50 to 6.426.42 points. Under interleaved routing, where each update involves one teacher, the two targets perform comparably. The phased results provide supporting evidence that the benefit may extend to signals accumulated across training phases. Target construction is thus an independent design axis in MOPD, complementary to teacher selection. The experiment repo could be find at https://github.com/HJSang/Delta-MOPD
Oct 7, 2026

A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching

Reinforcement Learning (RL) from outcome rewards suffers from sparse supervision, particularly on difficult, long-horizon tasks where successful trajectories are rare and costly to generate. On-Policy Distillation (OPD) offers an attractive alternative by providing dense token-level supervision from a stronger teacher along the student's own generations. Self-distillation methods further remove the need for a separate teacher model by conditioning the same policy on privileged information to serve as its own teacher. However, privileged conditioning alone does not guarantee that the resulting distillation update improves the student. Indeed, privileged information can lead the teacher to solve tasks through shortcuts unavailable to the student, producing supervision poorly matched to the student's current behavior. Consequently, even a higher-performing teacher can provide guidance that degrades student performance. To address this, we analyze how the choice of privileged teacher affects the student's update. We derive a necessary and sufficient condition for the teacher's local distillation update to be a positive multiple of the student's reward gradient. Our analysis suggests that the teacher should not only perform well on the task, but also provide guidance suited to the student's current capabilities. This characterization motivates a practical teacher-training surrogate that combines outcome rewards with token-level Kullback-Leibler (KL) regularization toward the student. Based on this result, we propose Joint On-Policy Learning and Teaching (JOLT), which jointly trains a single policy in two roles: a privileged teacher using a KL-regularized objective, and an unprivileged student using dense on-policy distillation. Across mathematical reasoning, coding, tool use, and terminal use, JOLT improves training efficiency and performance, with further gains from student rewards.
Oct 7, 2026

Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models

Looped Language Models (LoopLMs) offer a parameter efficient approach to scaling reasoning by reusing shared parameters across recurrent computation steps. Despite their promise, effective post-training of LoopLMs remains challenging. Existing approaches either provide reward based supervision that is sparse or costly to extend across loops, or rely on external teachers or privileged information, leading to limited teacher availability or teacher-student context mismatch. To address these limitations, we introduce LoopOPD, a cross-loop on-policy distillation framework that uses additional recurrent computation within a LoopLM as its own source of supervision. LoopOPD uses a frozen terminal loop policy as a compute privileged teacher for an intermediate loop student on student generated rollouts, providing dense supervision without an external teacher or privileged information. We further propose Dynamic LoopOPD (D-LoopOPD), which continually refreshes the terminal loop teacher as the shared model parameters are updated, enabling recurrent self-improvement. We characterize how distillation updates propagate across loop depths and derive sufficient conditions under which a single update yields simultaneous local improvement at both loop depths. Experiments on Ouro-Thinking models show that LoopOPD improves mathematical reasoning, while D-LoopOPD yields further gains through dynamic teacher updates. Despite being trained only on mathematical data, the resulting models also improve on general reasoning and code generation benchmarks, demonstrating that recurrent computation can serve as an effective source of supervision for LoopLMs. Our code and model checkpoints will be released upon acceptance.
Oct 7, 2026

On-Policy Distillation Teaches New Skills but Not New Knowledge

On-policy distillation (OPD) strengthens language-model reasoning, yet whether students acquire new factual knowledge or compositional skill for multi-step reasoning remains unknown. We separate these capabilities using a controlled synthetic framework that measures the student's initial capabilities and independently controls the teacher's additional facts, compositional skill, or both. Across four models from three families, reverse-KL OPD reliably transfers compositional skill across unseen reasoning structures, but transfers minimal factual knowledge. Decoupling the distillation recipe reveals the source of this asymmetry: replacing reverse KL with forward KL restores factual transfer, whereas student rollouts specifically improve the execution of multi-step reasoning. Experiments on recent factual QA and competition mathematics show a similar asymmetry under reverse-KL OPD, yielding notable reasoning gains without factual memory expansion. Together, these results demonstrate that on-policy distillation does not expand a model's parametric knowledge, but instead teaches it to organize and compose the knowledge it already possesses.
Oct 7, 2026

OnlineQAT: On-Policy Distillation for Ultra-Low-Bit Large Language Models

Quantization-aware training (QAT) can recover much of the accuracy lost when large language models are compressed below four bits. Existing re- covery stages, however, are commonly optimized on fixed completions or teacher-generated answers, whereas the deployed quantized model condi- tions on prefixes generated by itself. Quantization errors can therefore move the model into states that are absent from offline recovery data. We introduce OnlineQAT, a two-stage framework that first obtains a usable low-bit initialization through block-wise QAT and then performs on-policy distillation (OPD) on student-generated responses. At each visited pre- fix, a frozen full-precision teacher provides a sampled reverse-KL training signal. On Qwen3-1.7B, OnlineQAT obtains the best average among the compared quantized methods: 57.28 at W3A16 and 32.52 at W2A16, im- proving over ReasoningQAT by 2.90 and 0.44 points, respectively. The results suggest that student-visited states provide a useful recovery signal beyond fixed-completion training, particularly at three bits.
Oct 6, 2026

TAP: Efficient Long-Horizon Agent Pruning via Trajectory-Anchored Recovery

Emerging long-horizon agentic tasks require repeated model calls, worsening the inference cost of already-costly language models. While narrow agentic tasks suggest potential for aggressive model pruning without performance drop, empirical results show existing methods proposed for question answering tasks severely degrade task performance when applied to agentic models. We trace this failure to two decisions: what to prune and how to recover. For pruning, one-shot importance estimates fail to track how the pruned model adapts. For recovery, offline distillation covers only teacher prefixes, while full-trajectory on-policy distillation causes student errors to compound across turns. In this work, we propose Trajectory-Anchored Pruning (TAP), the first structural pruning framework for reinforcement learning (RL)-trained agents. TAP couples structural pruning with efficient on-policy recovery, anchoring interactions to teacher trajectories while allowing the student to generate each reasoning-action response. A frozen dense teacher supervises the student's response prefixes, addressing within-response training-inference mismatch while preventing student-induced deviations from propagating across training turns. Instead of one-shot pruning, TAP re-scores channels using gradients of the recovery objective on the recovered student, connecting iterative channel selection to the evolving policy. With 60% of FFN channels removed, TAP retains 99.2% and 88.0% of the dense 7B agents' task success rates on ALFWorld and WebShop, respectively, while reducing GPU time per successful task by approximately 22% and 17%. These results demonstrate effective structural compression of long-horizon agents under a limited recovery budget.
Oct 6, 2026

GraphOPD: Graph-Augmented On-Policy Distillation for LLM Agents

On-policy distillation post-trains large language model agents by supplying dense, step-level guidance from a teacher policy when the reinforcement-learning reward is sparse and arrives only once per trajectory. Existing instantiations allocate this guidance by the size of the teacher-student divergence at each step, on the single-turn intuition that a large disagreement marks a mistake worth correcting. Once decisions chain over many turns, that rule misfires, since an early drift enters every later context both policies condition on, leaving the teacher consistent with the drifted trajectory instead of flagging its cause, while interchangeable steps register large but outcome-irrelevant divergences. We demonstrate this on an agentic benchmark, where distilling the highest-divergence steps brings no consistent benefit over random selection. To this end, we introduce GraphOPD, the first method to bring graph-based structural augmentation into on-policy distillation for agent capabilities. It reads which steps enabled which later ones from the environment's own record of state changes, immune to the drift that corrupts the teacher-student gap, organizes them into a dependency graph, scores each step by a random-walk stationary distribution over it, and fuses that structural credit with the divergence signal into a trajectory-relative mask concentrating supervision on each rollout's highest-aptitude steps. Across three model scales and eleven baselines on ALFWorld, WebShop, and SearchQA, GraphOPD shows competitive performance throughout, improving over the strongest baseline by up to +5.8 pp. An executed-replay audit further shows that this structural credit score tracks true causal impact far above chance, that both fused signals are independently necessary, and that the same signal transfers to out-of-domain tool-integrated reasoning.
Oct 6, 2026

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

On-Policy Distillation (OPD) trains a student on its own generations using teacher feedback. With different tokenizers, comparing teacher and student predictions requires alignment at both sequence and vocabulary levels. In this paper, we examine whether expanding this alignment coverage improves learning. Across three heterogeneous teacher--student pairs on mathematical reasoning and code generation, strict 1:1 groups already cover most student-generated tokens despite substantial vocabulary mismatch. On responses sampled from the students before distillation, the shared vocabulary retains nearly all teacher and student probability mass at strictly aligned positions on average. Restricting reverse KL to a student-selected top-16 subset of the shared vocabulary at each strict position achieves accuracy comparable to full shared-vocabulary OPD, outperforming the evaluated cross-tokenizer baselines. Adding mean squared error supervision on span log-probabilities in mismatch groups gives complete supervision coverage, yet reduces accuracy. At checkpoints from training with only the strict loss, the span gradients show weak or negative directional agreement with the strict gradients and grow in magnitude relative to them. These diagnostics may help explain the accuracy drop from adding span supervision. Our findings motivate a shift from maximizing alignment coverage to prioritizing supervision reliability: compact supervision at strict positions can be more effective than broader coverage that introduces weakly aligned or conflicting training signals.
Oct 6, 2026

UP-MOPD: Update Projection in Multi-Teacher On-Policy Distillation

On-policy distillation from multiple teachers combines expertise from different domains in a single student, but conflicting gradients can hinder this integration. Gradient corrections directly constrain parameter updates under plain SGD. With optimizers such as AdamW, however, momentum, adaptive scaling, and weight decay can turn a corrected gradient into an update that increases a domain loss to first order. To address this gap, we propose Update Projection for Multi-Teacher On-Policy Distillation (UP-MOPD). UP-MOPD lets the original mixed gradient update the optimizer state and generate a candidate displacement, then projects only violating candidates before they are committed to the parameters. The projection gives the unique feasible update closest to the candidate in Euclidean distance. In experiments combining medical and general domains, UP-MOPD improves IFEval-loose accuracy late in training by 2.96 points over vanilla M-OPD. It achieves an average score of 60.03 across eight metrics, compared with 59.00 for gradient projection and 59.15 for update rejection. On a public benchmark covering mathematics, code, and instruction following, it achieves the best average across six tasks (32.67), leads on LiveCodeBench v5, and ties for the best IFEval result.These results support projecting optimizer updates to reduce interference between domains.
Oct 6, 2026

On-Policy Distillation with Negative-Policy Rollouts

On-policy distillation (OPD) has been widely studied as a post-training method in which a student model obtains token-level supervision from a stronger teacher on its own rollouts. Recent studies have improved OPD through alternative distillation reward formulations and teacher configurations, while the objective of distillation remains centered on mimicking the teacher. However, when a stronger teacher has limited distributional overlap with the student, such positive guidance can provide insufficient learning signals. In this work, we introduce Negative-Policy OPD (NP-OPD), which complements teacher supervision with rollouts from a lower-performing, lower-capability negative policy that serves as a negative reference for the student. Rather than modifying the distillation reward formulation, NP-OPD introduces the negative policy at the rollout stage, continuously supplying tokens preferred by the negative policy over the teacher so that they remain exposed to teacher supervision throughout training. This provides an explicit negative signal through negative-policy rollouts while preserving the positive teacher supervision used in OPD. Through extensive experiments, we show that NP-OPD improves OPD across model scales, generation modes, reasoning domains, and different OPD variants. Furthermore, our analyses show that NP-OPD effectively suppresses tokens preferred by the negative policy over the teacher and moves the student away from the negative policy. These results support our design of introducing negative signals through negative-policy rollouts and provide new insight into the role of the rollout policy in OPD. Code will be available at https://github.com/naver-ai/np-opd.
Oct 6, 2026

Does On-Policy Distillation for Safety Pose Backdoor Risks?

On-policy distillation (OPD) has attracted growing attention as an effective way to transfer capabilities from teacher models to student models. Recent studies further explore OPD as a tool for improving large language model safety with promising results. However, these approaches typically assume that the teacher and training data are trustworthy. In this paper, we uncover an overlooked threat to OPD for safety: a safety-aligned but backdoored teacher can propagate its hidden malicious behavior to an initially clean student. Under our threat model, a poisoning rate as low as 3% results in an attack success rate (ASR) of up to 70% on the distilled student. We further identify two training choices that can amplify this risk. First, increasing the number of training epochs can lead to high ASR even at low poisoning rates. With only 10 poisoned samples, ASR reaches 67% after 16 epochs. Second, the commonly used top-k KL can accelerate backdoor transfer, causing trigger-conditioned harmful behavior to emerge earlier than sampled-token KL in most settings. Alongside these findings, we explore a simple mitigation, Lazy Defense, which clips KL rewards to make student updates less aggressive, limiting aggressive updates and slowing backdoor learning. Experiments show that Lazy Defense delays backdoor transfer in low poisoning rate settings. Together, our findings reveal that OPD can propagate backdoors, highlighting the need to address the safety risks of OPD.
Oct 5, 2026

Learning What to Distill: Bilevel Top-K Token Selection for Self-Distillation in Large Language Models

Large language models have shown strong reasoning capabilities, but their high inference costs make knowledge distillation an important approach for transferring such capabilities to compact models in resource-constrained scenarios. On-policy self-distillation further reduces the reliance on external large teacher models while improving the reasoning ability of compact language models. However, existing methods typically either distill all token positions uniformly or select tokens using fixed heuristic criteria, assigning the same distillation strength to the selected positions rather than adaptively learning which tokens are most beneficial for distillation. To address these limitations, we propose BiToK-SD (Bilevel Top-K Token Selection for Self-Distillation), a bilevel-optimization-based token selection method that learns where distillation should be applied during on-policy self-distillation. Specifically, BiToK-SD is formulated as a bilevel optimization problem, where the lower-level problem models Top-K token selection as a differentiable threshold-based relaxation, allowing the selected positions to adapt as the student policy evolves, while the upper-level problem performs knowledge distillation on the selected positions. Experiments on mathematical reasoning benchmarks show that BiToK-SD achieves the best average performance among all compared methods while requiring only lightweight additional computation.
Oct 5, 2026

Sharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution

A language model can give a correct answer more probability than any single incorrect answer and still usually sample an incorrect one, because the incorrect answers together hold more probability. The power distribution raises each complete answer's probability to a power above one and renormalizes, shifting probability toward answers the model finds most likely (sharpening). Sampling from it improves reasoning without changing parameters, but needs many scored candidates per query. We show that a model can instead be trained to produce such answers in one generation. On-policy power distillation (OPPD) runs a sequential Monte Carlo sampler in which the model being trained generates candidates and a frozen teacher's power distribution weights them; the same probabilities weight each answer in a maximum-likelihood update. Training raises single-generation accuracy by up to 23.0 points on MATH500 and 27.3 on GSM8K over the untrained model at the same temperature, and one generation scores 2.4 and 3.5 points above published power sampling with 64 candidates, recovering 94 percent of the gain that 16 candidates give the untrained model. For context, against GRPO trained with verified rewards from the same checkpoint and budget, OPPD scores 3.8, 4.0 and 5.4 points higher on MATH500, GSM8K and AIME using no reference answers; the two are complementary, and OPPD applied after GRPO adds up to 9.3 points. Trained only on mathematics, OPPD raises HumanEval accuracy by up to 5.3 points. One loss coefficient moves the sharpening exponent the model absorbs between 1.19 and 2.02, against 1.14 for ordinary on-policy distillation, and it rises mostly on the model's own answers. Gains hold across model families and sizes, including a model already trained with verified rewards, where lowering the temperature gives nothing and OPPD adds 4.4 points on MATH500. Code: https://github.com/ArminAzizi98/OPPD.
Oct 5, 2026

Learning What to Imitate: Entropy-Aware Distribution Mixing

Small language models are often post-trained as students on reasoning traces from stronger teacher models to efficiently learn new skills. However, token-level imitation on traces that lie far outside the student's expected distribution often produces confident conflicts, whereby the student is required to imitate a continuation that it deems unlikely (i.e., low-probability) despite being confident in a different continuation (i.e., in a low-entropy state). To mitigate the degradation in generalisation and catastrophic forgetting caused by these conflicts, we propose Entropy-Aware Mixing: a dynamic per-token interpolation of the student and teacher distributions, gated by the student's predictive entropy. We implement both convex and geometric interpolations for both offline trace generation (via speculative decoding, then SFT) and on-policy forward-KL distillation. Our results show that entropy-aware mixing stabilises distillation, improving in-distribution and out-of-distribution math reasoning while better preserving general capabilities than fixed-teacher supervision. Nonetheless, the optimal entropy schedule depends on the training source, with offline-generated traces favouring concave schedules (greater overall teacher influence) and on-policy training favouring linear or convex schedules (teacher concentrated in high-entropy states).
Oct 5, 2026

Flash-OPD: Fast On-Policy Distillation

On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but generating and evaluating long rollouts incurs substantial training cost. Existing acceleration methods reduce this cost through open-loop rollout schedules or closed-loop horizon adaptation. However, supervision compatibility can vary substantially across trajectories, making a single rollout horizon difficult to match their heterogeneous reliable lengths: an overly short horizon may truncate useful supervision, while an overly long one wastes computation beyond reliable regions. Our key insight is that the trajectory-specific reliability boundary need not be predicted before generation. By viewing reliability as the first-passage of accumulated low teacher--student compatibility events, the boundary is inherently unknown before sampling, yet whether it has been reached can be determined exactly from the observed prefix. Building on this insight, we propose Flash-OPD, which shifts from rollout-horizon control to adaptive trajectory-level boundary verification. Flash-OPD interleaves cached generation with teacher verification and independently stops each trajectory according to its observed compatibility events. To reduce verification overhead, the recent event rate is used only to schedule the next verification point, while the actual stopping decision always relies on the exact cumulative count. This separation prevents estimation errors from causing premature termination while enabling efficient verification during generation. Extensive experiments across diverse datasets and teacher--student settings show that Flash-OPD achieves 2.2×2.2\times--7.5×7.5\times speedups over standard OPD while maintaining or improving accuracy.
Oct 5, 2026

Transfer-Stratified On-Policy Distillation for RL-Improved Reasoning Teachers

Reinforcement learning can substantially improve a reasoning teacher, but it is unclear which of those improvements survive when the teacher supervises a smaller on-policy student. We study this question in mathematical reasoning by comparing teacher lineages before and after GRPO, multiple student scales, direct GRPO, and several on-policy distillation objectives. The central finding is that transfer is structured rather than scalar: teacher strength alone does not make dense distillation competitive, while an RL-improved teacher creates useful but metric-dependent student gains. This motivates Transfer-Stratified On-Policy Distillation (TS-OPD), which screens training problems by the joint sampled success of the student and teacher, routes acquisition problems to gated forward KL, routes consolidation problems to gated reverse KL, and adds an entropy brake to protect sampled coverage. Across the main comparison, TS-OPD is the strongest student objective for macro average correctness with the GRPO-improved teacher, while pass@K remains more mixed. Ablations show that the gains come from routing and token gating rather than skipping problems. These results support a transfer-aware view of OPD: stronger teachers help when the supervision direction and token budget match the student's observed ability, not merely because the teacher endpoint is stronger.
Oct 5, 2026

ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning

Language models are moving beyond generating answers to pursuing long-horizon goals in interactive environments. Post-training these agents requires long, heterogeneous trajectories, and synchronous systems leave learner engines idle until rollout and verification finish. To squeeze out these pipeline bubbles, asynchronous training overlaps rollout and learning across updates, but comes at the cost of policy staleness. We introduce ThunderSyncRL, which starts gradient computation as soon as all required inputs are fixed, without policy staleness. For group relative policy optimization (GRPO), ThunderSyncRL computes each trajectory's score gradient as soon as the reward for that trajectory arrives, without waiting for the group. For on-policy distillation (OPD), it computes gradients for each completed agentic turn's teacher-scored actions while tool calls run in the sandbox. We prove that gradient streaming produces the same GRPO and OPD updates as batch-synchronous training, without changing either objective. On SWE-bench Verified and Terminal Bench 4.0, we train models to the same performance up to 1.9×1.9 \times faster than synchronous training. With zero policy staleness, ThunderSyncRL also outperforms asynchronous training at a fixed budget by up to 2.472.47 percentage points.
Oct 5, 2026

Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning

A long-standing goal of AI is a model that can continually learn and improve itself. On post-trained models, supervised finetuning (SFT) on new data often causes poor generalization and catastrophic forgetting. As such, the conventional wisdom is that on-policy training is a prerequisite for continual learning. In practice, however, data containing new knowledge or capabilities are often off-policy. While methods such as on-policy self-distillation (OPSD) try to bridge this gap by converting off-policy data into on-policy signal, they have been shown to cause reasoning collapse. In this paper, we show that off-policy merging beats OPSD for continual learning. We first show that SFT learns a useful signal from new data, but naively applying its update interferes with existing capabilities. We reduce this interference with a simple recipe we term grafting, which changes where the update is learned and how it is applied: (1) learning the update on an earlier donor checkpoint, ideally even before the end of pretraining, and applying the weight update to the post-trained model; (2) scaling the weight update, equivalent to a form of model merging; and (3) optionally, masking the most sensitive update directions when the new data distribution is far from the post-trained model. Across continual learning settings including (1) distilling from expert traces, (2) self-improvement with STaR and Pedagogical RL, and (3) injecting knowledge after pretraining cutoff, grafting Pareto-dominates both SFT and OPSD in new-task and old-task performance, while avoiding expensive on-policy sampling. Therefore, our work challenges on-policy training as a necessity for continual learning on RL-trained models.
Oct 5, 2026

Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented Tuning

Post-training quantization has been shown to preserve VLA performance under standard evaluation conditions, but whether it preserves the full-precision model's robustness and generalization remains underexplored. In this study, we systematically study the robustness and generalization of post-quantized VLA policies under environmental disturbances. Empirical results show that quantized policies can become fragile to subtle environmental variations despite retaining comparable in-distribution performance. We further observe that action discrepancies are concentrated in a small subset of rollout states, while teacher guidance has opposite effects depending on discrepancy: it improves generalization at high-discrepancy states but can degrade it at low-discrepancy states. These findings reveal that effective post-quantization recovery requires selectively intervening on vulnerable states rather than globally distilling the student. We therefore propose Policy-Induced Vulnerability-Oriented Tuning (PIVOT-Q), a vulnerability-aware On-Policy Distillation (OPD) framework that selectively corrects vulnerable states encountered during quantized-student rollouts using the frozen full-precision policy as a teacher. PIVOT-Q identifies vulnerable states using discounted accumulated discrepancies over a short horizon, applies phase-balanced sparse supervision, and uses a Behavioral Anchor to prevent unnecessary changes. Experiments under seven LIBERO-Plus environmental variations demonstrate consistent recovery across multiple VLA backbones and quantization methods. Notably, PIVOT-Q consistently outperforms full-state distillation across all settings while using only 7.4% of its state-level distillation budget. Our code is available at https://github.com/ruanruan-andy/PIVOT-Q.
Oct 4, 2026

Towards Unbiased On-Policy Distillation for Block Diffusion Language Models

On-policy distillation (OPD) has emerged as an effective post-training paradigm for language models, with recent efforts extending it to block diffusion language models (BDLMs). However, existing studies focus almost exclusively on small block sizes, leaving distillation into student models with larger blocks underexplored. In this work, we investigate this regime and reveal two critical optimization biases that induce severe training instability. First, mismatched block boundaries between teacher and student cause context misalignment, providing distorted supervisory signals that misguide student decoding. Second, even under aligned contexts, an intrinsic optimization bias in OPD, where the student tends to rapidly absorb high-support signals while lagging on low-support updates, drives a premature confidence surge that traps weaker students in catastrophic overconfidence collapse. To resolve these, we propose \mbox{Un-OPD}, an unbiased on-policy distillation framework with two novelties for stabilizing BDLM training. First, Un-OPD introduces a boundary-aware step filtering strategy that eliminates context-misaligned decoding steps. Second, Un-OPD proposes moderating optimization intensity at high-support positions via a support-rebalanced confidence calibration, thereby bypassing overconfidence collapse. Beyond stability, we also introduce a rollout reuse mechanism to reduce rollout generation overhead. Extensive experiments on math reasoning and code generation benchmarks show that Un-OPD consistently stabilizes training and delivers superior performance while reducing wall-clock training time by approximately half.
Oct 4, 2026

How Should Teachers Be Prepared? RL on Student-Induced States for On-Policy Distillation

On-policy distillation (OPD) improves the reasoning capabilities of small language models through token-level teacher supervision on student-generated trajectories. Yet can teachers that excel at solving problems independently also guide student reasoning effectively? Prior work shows that when student prefixes follow reasoning paths that differ from the teacher's own or contain errors, teachers can be less accurate when continuing from these prefixes than when solving problems independently. To this end, we propose Prep-OPD, which uses reinforcement learning (RL) before distillation to train the teacher to adapt to the student's existing reasoning state and correct course when errors arise. Training optimizes teacher continuations from fixed student prefixes using final-answer correctness as the reward. The prepared teacher then trains the student through trajectory guidance and token-level supervision. We evaluate Prep-OPD on eight mathematical reasoning benchmarks, using Qwen3-4B-Instruct-2507 as the teacher and Qwen3-0.6B and Qwen3-1.7B as students. With the 4B teacher and 1.7B student, Prep-OPD improves average accuracy over standard OPD and the strongest baseline, Relay-OPD, by 8.28 and 2.30 percentage points, respectively. Controlled experiments further show that teacher RL conditioned on student-generated prefixes yields higher student accuracy than problem-start teacher RL with and without handoff on Qwen3-1.7B. Reusing the same prepared teacher also improves Qwen3-0.6B.
Oct 4, 2026

ResOPD: Tail Residualization for Sparse On-Policy Distillation

On-policy distillation (OPD) trains a student model on self-generated trajectories, but transmitting dense teacher distributions across long reasoning traces creates prohibitive communication and memory bottlenecks. Practical systems therefore rely on sparse teacher interfaces, typically transmitting either the sampled-token score or a small Top-kk distribution. However, this sparse setting faces a fundamental dilemma: sampled-token estimators are unbiased but suffer from severe gradient variance, whereas directly optimizing Top-kk objectives introduces systematic bias. To improve this trade-off, we propose ResOPD (On-Policy Distillation with Tail Residualization), which provides unbiased full-vocabulary reverse KL gradient estimation under on-policy sampling, with substantial variance reduction under the same sparse payload in the evaluated settings. ResOPD aggregates the unobserved vocabulary into an observable coarse tail event, computes its exact aggregate gradient, and samples only the fine-grained within-tail residual, which requires no additional teacher queries or forward passes. Extensive experiments demonstrate that ResOPD substantially reduces gradient variance, stabilizes online training dynamics, and improves downstream performance across the evaluated settings. These results establish ResOPD as an efficient, plug-and-play variance reduction primitive for sparse on-policy distillation.
Oct 3, 2026

DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation

On-policy distillation (OPD) has emerged as a widely used paradigm for post-training large language models, reducing the train--test mismatch of conventional distillation by supervising the student on its own generated trajectories. However, existing OPD objectives remain largely token-local and outcome-agnostic, optimizing teacher--student agreement at each prefix despite reasoning quality being determined at the trajectory level. Reinforcement learning with verifiable rewards (RLVR), particularly Group Relative Policy Optimization (GRPO), provides complementary outcome-level supervision but suffers from sparse rewards and coarse credit assignment. We show that OPD and RLVR exhibit complementary blind spots: teacher signals provide dense local guidance but are weakly aligned with rollout correctness, whereas group-relative rewards capture task success but provide coarse token-level credit and vanish on all-failure groups. We introduce DiffGate, an outcome-gated objective that combines GRPO with selective, bounded teacher guidance. Teacher supervision is applied only to failed trajectories, scaled by group difficulty, and smoothly bounded to prevent extreme teacher--student discrepancies from dominating optimization. The verifier therefore determines which trajectories receive teacher guidance, while the teacher provides dense token-level update directions within those trajectories. Across Qwen3-0.6B and Qwen3-1.7B students, DiffGate improves code avg@8 over matched GRPO by +1.7+1.7 and +1.8+1.8 points and pass@8 by +1.6+1.6 and +5.7+5.7 points, respectively. On mathematics, avg@8 remains within 0.50.5 points of GRPO while pass@8 improves by +1.1+1.1 and +3.9+3.9 points. Overall, DiffGate improves pass@8 across all four model--domain settings, demonstrating improved solution coverage under our evaluation protocol.