arXiv:2608. 14728v1 Announce Type: cross Abstract: On-policy distillation (OPD) has emerged as an effective paradigm for transferring knowledge between language models, where a student is trained to align its next-token distribution with the teacher's along its own trajectories.
arXiv:2606. 22600v2 Announce Type: replace-cross Abstract: On-Policy Distillation (OPD) improves the learning efficiency of standard reinforcement learning through dense, token-level supervision from teachers.
The paper investigates how the sampled-token reverse-KL loss in on‑policy distillation distributes updates across tokens. By analyzing the gradient of the per‑token K2 estimator, the authors find that tokens with low student probability and large teacher‑student gaps receive disproportionately large gradient norms. They propose Surprise‑aware Reweighting (SuRe), a lightweight weighting rule that further amplifies this allocation, and demonstrate that SuRe improves math metrics on Qwen3 student models without harming out‑of‑domain performance.
The paper investigates on‑policy distillation (OPD), showing that teacher supervision during OPD contains significant noise that grows with teacher size, yet the student policy remains largely unaffected by this noise. It finds that OPD’s gains stem mainly from suppressing low‑log‑probability tokens, a process that can be replicated without a teacher. Building on this insight, the authors propose On‑Policy Self‑Adaptation (OPSA), a supervision‑free method that uses entropy‑adaptive negative advantages to improve performance on several benchmarks, outperforming both the base model and OPD.
arXiv:2608.29846v1 Announce Type: cross Abstract: Sampled-token on-policy distillation (OPD) efficiently transfers capabilities from teacher to student using student-generated tokens, requiring teach...
On-policy distillation (OPD) trains a student on its own generated responses using dense, token-level supervision from a stronger teacher. Vanilla OPD treats all teacher signals equally, assuming that...
The paper introduces Selective Supervision for Direct-OPD (S$^2$D-OPD), a refinement of Direct On-Policy Distillation that filters out states where the teacher’s policy change is minimal, as measured by the teacher‑reference Jensen‑Shannon divergence. By masking low‑divergence states and keeping only the top 10% of states per response, S$^2$D-OPD improves held‑out accuracy on AIME and HMMT benchmarks across multiple teacher‑student pairs without additional forward passes.
arXiv:2609.39275v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own generated prefixes with token-level teacher feedback, but transmitting or storing the teacher'...
arXiv:2608. 09836v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement, where students exploit repetitive loops to achieve near-perfect token agreement with the teacher despite globally flawed responses.
arXiv:2607. 04037v1 Announce Type: cross Abstract: On-policy distillation is a powerful way to transfer reasoning ability from a strong teacher to a smaller student: the student samples trajectories from its own policy, and the teacher provides dense token-level supervision on the states the student actually visits.
arXiv:2607. 16955v1 Announce Type: cross Abstract: On-policy knowledge distillation transfers reasoning from large teachers to compact students, but existing approaches suffer three compounding failure modes: (i) cold-start collapse, where a fresh student assigns near-zero mass to teacher-preferred tokens; (ii) state-agnostic divergence scheduling, where time-only forward/reverse-KL interpolation ignores the student's coverage state; and (iii) binary reward sparsity, where pass/fail signals discard information from partially correct traces.
The paper investigates the statistical properties of Reverse‑Kullback‑Leibler (KL) policy distillation, focusing on how different feedback settings affect sample complexity. It shows that when the teacher reveals its full action distribution, online distillation achieves minimax rates, whereas revealing only the probability of the student‑generated action requires substantially more data. In contrast, offline distillation attains the same minimax rate regardless of whether the teacher’s full distribution or only the probability of the teacher‑generated action is revealed, because teacher‑generated actions expose the teacher’s preferences directly.