arXiv Computation and Language

Recursive Self-Improvement via On-Policy Distillation for Reasoning

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 AI
6d ago

Bootstrapped On-Policy Distillation

Bootstrapped On-Policy Distillation (BOPD) is a two‑stage framework that first uses on‑policy self‑distillation (OPSD) to capture task‑relevant knowledge from reference‑conditioned supervision into an intermediate model, and then distills this intermediate model into a fresh copy of the initial model. The approach addresses the degradation observed in OPSD during continued training, which is caused by a growing mismatch between the evolving student and the frozen teacher. Experiments demonstrate that BOPD improves mathematical reasoning and code generation beyond both the initial models and the constructed OPSD teachers.

By Yue Wu, Xueyu Zhou, Yangrong Hu, Jian Huang
arXiv AI
Sep 7

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

RISE (Recursive Improvement via Self-Extrapolating Policy Distillation) is a new method that builds a synthetic teacher from a language model’s own RLVR training trajectory. By extrapolating the displacement between the current checkpoint and a trailing anchor in parameter or logit space, RISE transforms sparse outcome-based updates into dense token-level targets without external models or privileged conditioning. The approach recursively refines the student model, combining RLVR and on‑policy distillation, and demonstrates superior performance across mathematical reasoning, STEM, code generation, and multi‑turn agentic tasks.

By Yang Li, Semih Yavuz, Shafiq Joty
arXiv Machine Learning
Jul 22

H$^2$SD: Hybrid Hindsight Self-Distillation

arXiv:2607. 18955v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models on tasks such as mathematical reasoning and code generation.

By Qiye Cai, Yichuan Ma, Linyang Li, Peiji Li, Yongkang Chen, Qipeng Guo, Yicheng Zou, Tao Gui, Xiaocheng Feng, Bing Qin
arXiv Machine Learning
Oct 2

Activation-Conditioned Self-Distillation

Activation-Conditioned Self-Distillation (ACSD) is a new on‑policy self‑distillation method that uses a frozen copy of the base model to extract a steering vector by contrasting activations from self‑generated trajectories that reach verified correct answers with all other trajectories. The student learns from next‑token distributions on its own prefixes, without needing reference text or teacher parameter updates, and is used alone at inference. Across five models, ACSD achieves the highest mean accuracy on four mathematical benchmarks, with notable gains on DeepSeek‑R1‑0528‑Qwen3‑8B and LiveCodeBench v6 compared to the OPSD baseline.

By Zhexi Lu, Subhajit Chaudhury, Tejaswini Pedapati, Keerthiram Murugesan, Lei Yu
arXiv Machine Learning
Oct 8

A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching

The paper introduces Joint On-Policy Learning and Teaching (JOLT), a method that trains a single policy to act both as a privileged teacher and an unprivileged student. It derives a condition ensuring the teacher’s distillation update aligns positively with the student’s reward gradient, leading to a KL‑regularized teacher objective that matches the student’s current capabilities. Experiments show JOLT improves training efficiency and performance across various tasks, with additional gains when student rewards are incorporated.

By Randy Ardywibowo, Arnav Dalal, Jiantao Jiao
arXiv AI
Oct 1

On the Off-Policy Teacher in On-Policy Distillation

The paper introduces SCOUT, a co‑training framework that adapts an off‑policy teacher to better continue from student‑generated prefixes in on‑policy distillation (OPD). By periodically optimizing the teacher’s conditional continuation ability using reinforcement learning with verifiable rewards, SCOUT improves the teacher’s performance on student prefixes. Experiments across various teacher‑student setups, model scales, and reasoning domains show that SCOUT consistently enhances the effectiveness of OPD.

By Langlin Huang, Hao Liu, Mononito Goswami, Xinyu Li, Prithwith Jana, Nikos Kanakaris, Patrick Bl\"obaum, Purak Jain
arXiv Machine Learning
Aug 20

Rethinking Privileged Information in On-Policy Self-Distillation

The paper investigates on‑policy self‑distillation (OPSD), where a student model learns from its own outputs using token‑level supervision conditioned on privileged reference information. Experiments with Qwen3 models on science and mathematics datasets show that the correct reference does not consistently improve performance; students can improve without it, and solutions from other problems sometimes outperform the correct reference. The study finds that student predictions align more closely with the base model’s reasoning than with the reference supervision, and that alignment alone does not reliably predict performance gains.

By Samyak Shrestha, Alexander Tessier