arXiv:2607. 22629v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time.
The paper investigates how privileged information—such as a teacher’s full solution or reasoning trace—affects on‑policy self‑distillation (OPSD) in language models. Using the AMPLE‑Math benchmark, the authors compare distillation with and without extra teacher views, finding that reference‑free distillation explains most gains for Qwen3‑1.7B, while additional references provide modest benefits, especially for polished solutions. The study also shows that the impact of privileged data depends on the student’s training regime and that altering token‑level supervision can leave student behavior largely unchanged.
The paper reviews On‑Policy Self‑Distillation (OPSD), a method where a language model learns from its own generations using privileged information such as reference solutions or plans, eliminating the need for a larger teacher model. It identifies a key failure mode—collapse, where the model’s reasoning paths narrow progressively—and analyzes it through three levers: signal application, privileged information, and teacher dynamics. The review focuses on mathematical reasoning, offering a unified vocabulary and distinguishing settled facts from ongoing debates.
arXiv:2607. 05184v1 Announce Type: new Abstract: Self-distillation is a promising recipe for self-improvement in language models.
arXiv:2607. 14552v1 Announce Type: cross Abstract: A standard recipe for distilling the reasoning ability of large language models (LLMs) is to sample chains of thought from the model, keep those that reach the correct final answer, and fine-tune on the survivors.
arXiv:2607. 26246v1 Announce Type: new Abstract: On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm for transferring capabilities across LLMs.
On-policy distillation trains a language model on its own generations while a teacher scores them token by token. It combines the dense supervision of imitation learning with the on-policy sampling of...
The paper introduces Zone of Proximal Policy Optimization (ZPPO), a method that keeps a teacher model inside prompts rather than in the policy gradient to improve knowledge distillation for small students. ZPPO creates two types of reformulated prompts—Binary Candidate-included Questions (BCQ) and Negative Candidate-included Questions (NCQ)—to expose students to correct and incorrect responses, and uses a replay buffer to focus training on hard questions until the student’s accuracy improves. Experiments on the Qwen3.5 family with a 27B teacher across 31 benchmarks show that ZPPO outperforms both off‑policy and on‑policy distillation methods, especially at the smallest student scales.
arXiv:2605. 09253v2 Announce Type: replace-cross Abstract: While recent work in Reinforcement Learning with Verifiable Rewards (RLVR) has shown that a small subset of critical tokens disproportionately drives reasoning gains, an analogous token-level understanding of On-Policy Distillation (OPD) remains largely unexplored.
arXiv:2609.37044v1 Announce Type: new Abstract: Explicit intermediate reasoning gives large language models (LLMs) a stronger problem-solving mode. We study learning from this think-mode advantage vi...
arXiv:2609.14193v1 Announce Type: cross Abstract: On-policy distillation (OPD) has become a standard component of frontier post-training pipelines, yet how much its training data actually contributes...
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.