Blockwise Policy-Drift Gating for On-Policy Distillation

• URL: http://arxiv.org/abs/2606.24084v1
• Date: Tue, 23 Jun 2026 02:58:16 GMT
• Title: Blockwise Policy-Drift Gating for On-Policy Distillation
• Abstract summary: On-policy distillation (OPD) trains a student policy using teacher signals computed on trajectories sampled by the student itself.<n>This paper introduces blockwise policy-drift gating, a lightweight student-only old-current drift controller for OPD under rollout reuse.
• Score: 14.61751557296924
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: On-policy distillation (OPD) trains a student policy using teacher signals computed on trajectories sampled by the student itself. Recent work shows that sampled-token OPD can be fragile on long-horizon reasoning tasks and that local teacher-support matching is a simple and effective repair. This paper introduces blockwise policy-drift gating, a lightweight student-only old-current drift controller for OPD under rollout reuse. The method computes log-probability shifts between the behavior student and the current student on the sampled token path, aggregates these shifts over fixed blocks or spans, and uses the resulting detached, mean-normalized gates to reweight OPD position losses. It does not change teacher targets, teacher top-K supports, or the rollout policy. In a six-variant Qwen3 math reasoning benchmark with a uniform 200-step training budget for all trained variants, we use pass@8 as the primary problem-level solve-rate metric. Fixed 64-token block gating improves sampled-token OPD mean pass@8 from 0.4978 to 0.5160 across AIME24, AIME25, MATH500, and AMC23. On Teacher-TopK/LSM, Block64 gives the best four-benchmark mean pass@8 among trained students. The results identify local old-current policy drift as a practical control signal for reused OPD rollouts and motivate block-level gating as a simple default for improving solve-rate robustness.

Related papers

• WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training [48.290951447286744]
  WDL-OPD is a mixture-constrained co-training method with two trainable policies.<n>An anchor policy generates every rollout, an auxiliary policy evaluates the same visited states, and a geometric mixture of their token distributions is matched to a frozen teacher by reverse KL.<n>We show that freezing the auxiliary recovers an anchor-plus-contrast proxy target closely related to OPD$2$ and W2S-OPD, whereas joint training creates branch-level degrees of freedom that a static delta cannot express.
  arXiv  Detail & Related papers  (2026-08-10T11:22:53Z)
• BOUND: Brief-Guided Corrective Preference Distillation at Search-Control Boundaries [82.41764922522565]
  BOUND is a brief-guided corrective preference distillation framework for persistent search drift.<n>It outperforms Trajectory SFT by 5.6 EM points on Bamboogle and 4.8 accuracy points on BrowseComp-Plus.
  arXiv  Detail & Related papers  (2026-08-09T15:32:16Z)
• DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation [9.897015521661915]
  On-policy distillation (OPD) trains student models on their own rollouts to reduce exposure bias.<n>Existing curriculum learning methods regulate how much teacher support is used according to training progress, but cannot determine when it is needed.<n>We propose DASH-OPD, a new agentic OPD method that can switch executors adaptively and bidirectionally.
  arXiv  Detail & Related papers  (2026-07-31T06:57:17Z)
• 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)
• Prefix-Guided On-Policy Distillation: Mining Golden Trajectories from Rollouts [48.550535291129584]
  Prefix-Guided On-Policy Distillation (PG-OPD) is a simple rollout-allocation framework that uses fixed-length prefixes to estimate trajectory value before expensive long-horizon generation.<n>Across diverse teacher-student combinations on AMC, AIME, and HMMT benchmarks, PG-OPD improves average accuracy by up to 4.80 points while reducing training time by up to 2.46x.
  arXiv  Detail & Related papers  (2026-06-20T11:18:34Z)
• OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification [21.095025092772257]
  On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher.<n>We introduce OmniOPD, a novel framework that addresses both limitations through a logit-free, chunk-level supervision signal.
  arXiv  Detail & Related papers  (2026-05-31T22:31:15Z)
• Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation [81.10000755917712]
  On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from a teacher.<n>As student-generated prefixes lengthen, the teacher's next-token distribution becomes less confident and less discriminative.<n>To mitigate SFD, we introduce textbfLookahead Group Reward (ours).
  arXiv  Detail & Related papers  (2026-05-29T04:39:20Z)
• Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training [20.04756350098974]
  In settings where labeled verifiable training data is the binding constraint, each checked example should be allocated to the model and reward density where it is most informative.<n>We identify a reward-density principle that governs this allocation: sparse sequence-level reward is most useful on models that can explore and discover better behavior, while dense token-level teacher supervision is better suited for compressing that behavior into a smaller deployment model.
  arXiv  Detail & Related papers  (2026-05-12T17:57:48Z)
• On-Policy Distillation with Best-of-N Teacher Rollout Selection [54.91780727674628]
  We propose BRTS, a Best-of-N Rollout Teacher Selection framework for on-policy distillation.<n>BRTS augments standard student-context OPD with a teacher-context supervision branch constructed from the teacher trajectory.<n>BRTS improves over standard OPD on challenging reasoning benchmarks, with the largest gains on harder datasets.
  arXiv  Detail & Related papers  (2026-05-10T19:49:00Z)
• 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)
• Rubric-based On-policy Distillation [62.11106822527392]
  On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box scenarios.<n>We contend that structured semantic rubrics can serve as a scalable alternative to teacher logits, enabling OPD using only teacher-generated responses.<n>We introduce ROPD, a simple yet foundational framework for rubric-based OPD. Specifically, ROPD induces prompt-specific rubrics from teacher-student contrasts, and then utilizes these rubrics to score the student rollouts for on-policy optimization.
  arXiv  Detail & Related papers  (2026-05-08T07:52:15Z)
• Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes [31.95045602299568]
  On-policy distillation (OPD) is appealing for large language model (LLM) post-training because it evaluates teacher feedback on student-generated rollouts rather than fixed teacher traces.<n>We revisit OPD from the estimator and implementation sides.<n>We identify three failure modes of sampled-token OPD: an imbalanced one-token signal, unreliable teacher guidance on student-generated prefixes, and distortions caused by tokenizer or special-token mismatch.
  arXiv  Detail & Related papers  (2026-03-26T15:35:59Z)

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.