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: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.
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.
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.
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:2606. 08432v1 Announce Type: new Abstract: On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision along the student's own rollouts.
arXiv:2607. 02502v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access.
On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories. This approach has achieved strong empirical gains and can often surpass conve...
arXiv:2609.36734v1 Announce Type: new Abstract: Knowledge Distillation (KD) trains a smaller-capacity student model to imitate a larger-capacity teacher model by matching output distributions, implic...
arXiv:2606. 00305v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) improves large language model reasoning by training a student model on trajectories sampled from its own policy under teacher supervision.
arXiv:2608. 14277v1 Announce Type: cross Abstract: On-policy distillation (OPD) offers a promising way to transfer reasoning capabilities from stronger teacher models, but applying it to long-context reasoning teachers and short-context students introduces practical challenges, including tokenizer mismatch, teacher-student distribution mismatch, response length explosion, and training instability.
arXiv:2609.36246v1 Announce Type: new Abstract: We present OLIVE (OnLine InterVEntion). At each iteration, the evolving student policy generates a new prefix, the teacher continues it autoregressivel...
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.