Multi-Rollout On-Policy Distillation via Peer Successes and Failures

• URL: http://arxiv.org/abs/2605.12652v1
• Date: Tue, 12 May 2026 18:57:44 GMT
• Title: Multi-Rollout On-Policy Distillation via Peer Successes and Failures
• Abstract summary: Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning succeeds or fails.<n>On-policy distillation (OPD) offers denser token-level supervision by training on student-generated trajectories.<n>We introduce Multi-Rollout On-Policy Distillation (MOPD), a peer-conditioned distillation framework that uses the student's local rollout group to construct more informative teacher signals.
• Score: 31.731266689209914
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning succeeds or fails. On-policy distillation (OPD) offers denser token-level supervision by training on student-generated trajectories, yet existing methods typically distill each rollout independently and ignore the other attempts sampled for the same prompt. We introduce Multi-Rollout On-Policy Distillation (MOPD), a peer-conditioned distillation framework that uses the student's local rollout group to construct more informative teacher signals. MOPD conditions the teacher on both successful and failed peer rollouts: successes provide positive evidence for valid reasoning patterns, while failures provide structured negative evidence about plausible mistakes to avoid. We study two peer-context constructions: positive peer imitation and contrastive success-failure conditioning. Experiments on competitive programming, mathematical reasoning, scientific question answering, and tool-use benchmarks show that MOPD consistently improves over standard on-policy baselines. Further teacher-signal analysis shows that mixed success-failure contexts better align teacher scores with verifier rewards, indicating that the gains arise from more faithful, instance-adaptive supervision. These results indicate that effective on-policy distillation should exploit the student's multi-rollout trial-and-error behavior rather than treating rollouts as isolated samples.

Related papers

• SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation [28.886137823815826]
  We introduce Sparse Probing and Outcome-calibrated Targets OPD (SPOT)<n>SPOT addresses two coupled decisions, where to probe and what to distill, through an acquisition--exploration-exploitation procedure.<n>Experiments across multiple student models and reasoning benchmarks demonstrate the effectiveness of SPOT.
  arXiv  Detail & Related papers  (2026-08-05T03:59:24Z)
• H$^2$SD: Hybrid Hindsight Self-Distillation [61.71131241473028]
  Reinforcement learning with verifiable rewards (RLVR) provides reliable outcome supervision for language model reasoning.<n>Existing self-distillation methods add a privileged teacher but typically assign it a fixed role.<n>We introduce Hybrid Hindsight Self-Distillation ($mathrmH2mathrmSD$), which jointly adapts teacher context and update strategy to trajectory correctness.
  arXiv  Detail & Related papers  (2026-07-21T10:47:27Z)
• On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity [5.35852583397955]
  On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student.<n>We show that this could come at a hidden cost: rollout diversity decreases and pass@k curves flatten.
  arXiv  Detail & Related papers  (2026-06-24T17:59:02Z)
• A Formula-Driven Survey and Research Agenda for On-Policy Distillation [4.397842507533513]
  This survey studies OPD as a feedback-to-update problem rather than a single loss family.<n>We develop a formula-driven taxonomy from two routes -- direct distributional losses and policy-gradient-style log-ratio updates.
  arXiv  Detail & Related papers  (2026-06-22T03:09:21Z)
• Localizing Credit at the Divergence: Path-Conditioned Self-Distillation for LLM Reasoning [12.363923974156636]
  Reinforcement learning from verifiable rewards assigns a single scalar to each rollout.<n>On-policy self-distillation addresses this by letting the same model act as a teacher conditioned on privileged information.<n>We propose Hindsight Self-Distillation (HSD), which conditions the teacher on a successful peer rollout.
  arXiv  Detail & Related papers  (2026-06-14T03:37:27Z)
• HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation [50.53459634301361]
  HERO is a hindsight-enhanced self-distillation framework that uses next environment observations as locally aligned feedback.<n> HERO improves task success and reduces unnecessary turns over environment-feedback-only self-distillation and GRPO.
  arXiv  Detail & Related papers  (2026-06-10T01:35:34Z)
• Adversarial Dual On-Policy Distillation from Expressive Teacher [53.63143943452487]
  Flow Matching teacher is learned from demonstrations and co-trained with a lightweight student.<n>The teacher provides two complementary signals on student rollouts.<n>The action channel supplies dense local targets at student-visited states, stabilizing exploitation.
  arXiv  Detail & Related papers  (2026-05-26T14:38:03Z)
• Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation [49.117085054884676]
  On-policy distillation trains a student model on its own rollouts using dense feedback from a stronger teacher.<n>We operationalize this principle through a trajectory-specific release rule.<n> Experimental results across strong-to-weak distillation tasks indicate that this release rule consistently outperforms standard full-trajectory OPD.
  arXiv  Detail & Related papers  (2026-05-13T15:05:30Z)
• Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation [71.16738415436458]
  We introduce Reflection-Enhanced Self-Distillation (RESD), a framework that transforms raw failure feedback into an active source of corrective supervision.<n>RESD interprets failed trajectories by generating retrospective reflections to diagnose local errors, and curates a persistent global playbook.<n> Empirical evaluations on multiple continual learning tasks demonstrate that RESD substantially outperforms standard self-distillation baselines.
  arXiv  Detail & Related papers  (2026-05-12T20:46:05Z)
• OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning [19.98950359294245]
  We study on-policy self-distillation (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories.<n>Despite the performance gains of OPSD, we identify a common but often overlooked mismatch between teacher and student responses.
  arXiv  Detail & Related papers  (2026-05-12T17:00:53Z)
• Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning [66.52232008796294]
  Prune-OPD dynamically aligns training budgets with supervision quality.<n>It reduces training time by 37.6%--68.0% while preserving, and often improving, performance on challenging benchmarks.
  arXiv  Detail & Related papers  (2026-05-08T14:38:53Z)
• Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization [18.027254451537342]
  Existing self-distillation methods largely reduce learning to KL matching toward the context-augmented teacher model.<n>We propose textbfPreference-textbfBased textbfSelf-textbfDistillation (textbfPBSD), which revisits on-policy self-distillation through a reward-regularized perspective.
  arXiv  Detail & Related papers  (2026-05-06T15:31:50Z)
• Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe [53.40076304466524]
  We propose Uni-OPD, a unified OPD framework that generalizes across Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs)<n>Specifically, from the student's perspective, we adopt two data balancing strategies to promote exploration of informative student-generated states during training.<n>We develop an outcome-guided margin calibration mechanism to restore order consistency between correct and incorrect trajectories.
  arXiv  Detail & Related papers  (2026-05-05T12:15:21Z)
• TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents [55.27396165691312]
  We identify a key limitation of vanilla OPD in multi-turn agent settings, which we term Trajectory-Level KL Instability.<n>We propose TCOD, a framework that controls the trajectory depth exposed to the student and progressively expands it with a curriculum schedule.<n> Experimental results across four student-teacher pairs show that TCOD mitigates KL escalation and enhances KL stability throughout training, improving agent performance by up to 18 points over vanilla OPD.
  arXiv  Detail & Related papers  (2026-04-27T03:38:27Z)
• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models [44.041109669153506]
  On-Policy Self-Distillation (OPSD) is a framework where a single model acts as both teacher and student by conditioning on different contexts.<n>We demonstrate the efficacy of our method on multiple mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-01-26T17:56:50Z)
• Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones? [58.80794196076336]
  Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT)<n>We propose a novel distillation pipeline that transfers both responses and rewards.<n>Our method generates pseudo-rewards through a self-supervised mechanism that leverages the inherent structure of both teacher and student responses.
  arXiv  Detail & Related papers  (2025-02-26T20:50:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.