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

• URL: http://arxiv.org/abs/2606.22793v1
• Date: Mon, 22 Jun 2026 03:09:21 GMT
• Title: A Formula-Driven Survey and Research Agenda for On-Policy Distillation
• Abstract summary: 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.
• Score: 4.397842507533513
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: On-policy distillation (OPD) trains an LLM on states induced by the current or recent student policy: the student generates complete or partial rollouts, a teacher or self-teacher scores the resulting tokens under their generated contexts, and dense log-probability, logit, or distributional signals are converted into post-training updates. This survey studies OPD as a feedback-to-update problem rather than a single loss family. We develop a formula-driven taxonomy from two routes -- direct distributional losses and policy-gradient-style log-ratio updates -- and use it to organize core methods, verifier- or outcome-guided hybrids, industrial reports, framework implementations, failure modes, and stabilization recipes under explicit evidence boundaries. The taxonomy shows that OPD effectiveness depends not only on KL direction or teacher access, but also on state compatibility, support construction, temporal credit, vocabulary-level probability routing, gates and weights, and regularization. We further separate two mechanisms often conflated in sampled-token OPD stability discussions. Temporal credit asks how teacher-student log-ratio returns should weight sampled actions across a rollout; vocabulary routing asks where probability mass should move when negative feedback suppresses a sampled token. This distinction yields bias boundaries for immediate, return-to-go, discounted, and baseline-corrected estimators, motivates GAE-OPD as a value-based hypothesis for log-ratio returns, and motivates Counterfactual Routed OPD (CR-OPD) for routing probability mass toward teacher-supported, student-reachable alternatives. We close by mapping actionability diagnostics, failure mechanisms, case studies, open problems, and a reporting checklist onto the same feedback-to-update variables.

Related papers

• dOPSD: On-Policy Self-Distillation for Diffusion Language Models [52.60302464420127]
  Diffusion large language models generate text by iteratively denoising a masked sequence.<n>Supervised fine-tuning is off-policy and suffers from exposure bias, while reinforcement learning gives only sparse, sequence-level rewards.<n>On-policy self-distillation (OPSD) offers a promising alternative, using one model as both student and teacher.
  arXiv  Detail & Related papers  (2026-07-05T17:47:29Z)
• DemoPSD: Disagreement-Modulated Policy Self-Distillation [49.30809363804017]
  On-policy self-distillation has emerged as a practical method for training large language models.<n>DemoPSD steers the student toward a weighted geometric combination of the teacher and student distributions.
  arXiv  Detail & Related papers  (2026-07-02T17:58:29Z)
• Purified OPSD: On-Policy Self-Distillation Without Losing How to Think [52.879387744920415]
  We find that on-policy self-distillation (OPSD) consistently fails on long chain-of-thought (long-CoT) reasoning models.<n>We propose a two-step solution: first, we construct a reference-only teacher to isolate the non-transferable component of the supervision signal.<n>Second, we use pointwise mutual information (PMI) as the mechanism to transform this residual into a well-formed PMI target distribution.
  arXiv  Detail & Related papers  (2026-07-02T14:33:07Z)
• 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)
• Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation [60.55792673956761]
  We propose textbfRubric-Conditioned Self-Distillation, a framework that incorporates rubrics as structured, fine-grained feedback for on-policy self-distillation.<n>We evaluate on a diverse suite of science reasoning benchmarks and results show that rubric-conditioned self-distillation effectively converts rubric-level criteria into token-level guidance.
  arXiv  Detail & Related papers  (2026-06-17T17:54:04Z)
• Trajectory-Refined Distillation [25.346810464266497]
  Trajectory-Refined Distillation (TRD) is a trajectory-level correction method that revises the student's rollout under the teacher guidance while within on-policy support.<n> TRD can also be applied to on-policy self-distillation (OPSD), a parameter-sharing variant that uses the student model conditioned on privileged informations as the teacher.
  arXiv  Detail & Related papers  (2026-06-07T03:17:25Z)
• 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)
• Multi-Rollout On-Policy Distillation via Peer Successes and Failures [31.731266689209914]
  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.
  arXiv  Detail & Related papers  (2026-05-12T18:57:44Z)
• Interactive Critique-Revision Training for Reliable Structured LLM Generation [18.00222080273147]
  We propose DPA-GRPO, a paired-action training method for a two-player generator--verifier game with structured verifier interventions.<n>We analyze the unregularized game and show that positive probability on strictly lower-reward intervention or revision actions creates a profitable unilateral deviation.<n>Experiments on TaxCalc TY24 show that DPA-GRPO improves structured decision accuracy over zero-shot generation and generator-only RL baselines.
  arXiv  Detail & Related papers  (2026-05-08T17:00:38Z)
• Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning [79.88942231770629]
  Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs)<n>We formalize rollout pipelines with unified notation and introduce Generate-Filter-Control-Replay (GFCR)<n>We synthesize methods spanning RL with verifiable rewards, process supervision, judge-based gating, guided and tree/segment rollouts, adaptive compute allocation, early-exit and partial rollouts, throughput optimization, and replay/recomposition for self-improvement.
  arXiv  Detail & Related papers  (2026-04-08T00:53:29Z)
• Causal Imitation Learning Under Measurement Error and Distribution Shift [6.038778620145853]
  We study offline imitation learning (IL) when part of the decision-relevant state is observed only through noisy measurements.<n>We propose a general framework for IL under measurement error, inspired by explicitly modeling the causal relationships among the variables.
  arXiv  Detail & Related papers  (2026-01-29T18:06:53Z)
• Tape: A Cellular Automata Benchmark for Evaluating Rule-Shift Generalization in Reinforcement Learning [0.0]
  We present Tape, a controlled reinforcement-learning benchmark designed to isolate out-of-distribution (OOD) failure under latent rule shifts.<n>We provide (i) standardized OOD protocols, (ii) statistical reporting requirements, and (iii) information-theoretic identities connecting entropy reduction to conditional mutual information.
  arXiv  Detail & Related papers  (2026-01-08T08:05:42Z)
• Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior [58.751981587234916]
  This paper formalizes the Refinement Provenance Inference (RPI) audit task as Refinement Provenance Inference (RPI)<n>We propose RePro, a logit-based framework that fuses teacher-forced likelihood features with logit-ranking signals.<n>During training, RePro learns a transferable representation via shadow fine-tuning, and uses a lightweight linear head to infer provenance on unseen victims without training-data access.
  arXiv  Detail & Related papers  (2026-01-05T10:16:41Z)
• Time-series Generation by Contrastive Imitation [87.51882102248395]
  We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy. At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
  arXiv  Detail & Related papers  (2023-11-02T16:45:25Z)
• L2R2: Leveraging Ranking for Abductive Reasoning [65.40375542988416]
  The abductive natural language inference task ($alpha$NLI) is proposed to evaluate the abductive reasoning ability of a learning system. A novel $L2R2$ approach is proposed under the learning-to-rank framework. Experiments on the ART dataset reach the state-of-the-art in the public leaderboard.
  arXiv  Detail & Related papers  (2020-05-22T15:01:23Z)

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.