On-Policy Self-Distillation (OPSD) aligns a student model’s token-level distribution with that of its self-teacher prompted by privileged context, but often fails to achieve continuous performance gains due to unreliable guidance on certain samples. Teacher-Evolution Self-Distillation (TESD) addresses this by allowing the self-teacher to generate rollouts and receive environmental feedback based on task correctness and context independence, enabling teacher-oriented optimization to enhance self-teaching capability. TESD also estimates teacher guidance reliability from these rewards and applies adaptive student-oriented optimization to down-weight unreliable samples, consistently outperforming representative token-level and sequence-level methods across multiple datasets and model scales.
arXiv:2606. 26091v1 Announce Type: new Abstract: On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student, with the teacher conditioned on a correct demonstration to provide dense token-level feedback.
The paper introduces a recursive self-improvement framework for language models that replaces an external teacher with a frozen copy of the student, enabling dynamic co-evolution (DCE) and self-refined concise learning (SRCL). DCE allows the privileged teacher to evolve alongside the student, while SRCL trains on shorter, verified rewrites to reduce verbosity. Experiments show that the combined DCE+SRCL approach outperforms traditional on‑policy self‑distillation across multiple model sizes and math benchmarks, achieving significant accuracy gains and shorter outputs.
arXiv:2608. 07935v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) adapts a language model by distilling guidance from a frozen teacher on trajectories sampled from the student.
Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Recent work suggests that on-policy learning can mitigate forgetting, with on-policy self-distillation emerging as a particularly attractive approach.
arXiv:2605.10889v2 Announce Type: replace-cross Abstract: On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions...
arXiv:2608. 12957v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) learns from reward differences within a rollout group, but receives no useful relative signal when every sampled response is incorrect.
arXiv:2607. 01763v1 Announce Type: new Abstract: Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities.
Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain. Recent annotation-free self-evolution methods address this by using the model's own outputs as supervision signals, constructing a teacher via additional context and aggregating predictions across multiple rollouts through majority voting to produce pseudo-labels.
arXiv:2608. 09745v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) converts feedback into dense token-level supervision on trajectories generated by the policy to be optimized, providing a useful complement to reinforcement learning with sparse outcome rewards.
The paper introduces Advantage-Based On-Policy Distillation (AOPD), a method that selectively weights teacher actions during online policy distillation by their counterfactual advantage to the student. Unlike standard OPD, which follows the teacher at every state, AOPD reinforces only those teacher actions that improve the student's expected outcome, using an estimator that relies solely on standard student rollouts and terminal rewards. Experiments on math, coding, and Medqa tasks demonstrate that AOPD outperforms both distillation and reinforcement learning baselines in external-teacher and self-distillation settings.
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.
The paper introduces TISD, a trajectory-intervention self-distillation method that forces a teacher-selected branch action and then lets the student generate the suffix, distilling the full trajectory under a privileged-context-conditioned teacher. This approach addresses a data-collection bottleneck in on‑policy self‑distillation by exposing successor contexts that the student would otherwise miss. Experiments on coding and science domains show modest but consistent improvements in average performance metrics compared to baseline methods.