paper-with-me

Papers

RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation

2026-06-10 · Leyi Pan, Shuchang Tao, Yunpeng Zhai, Lingzhe Zhang, Zhaoyang Liu, Bolin Ding, Aiwei Liu, Lijie Wen arxiv

On-policy self-distillation (OPSD) provides dense, token-level supervision for reasoning models by aligning a model's own distribution with the distribution it produces under privileged context, typically a verified solution. However, we show that the learning signal drawn from this distributional gap concentrates on style tokens rather than task-bearing ones, as the hinted model tends to produce more direct, shorter outputs. We term this pathology \emph{privilege-induced style drift}, which destabilizes training or causes response length to shrink. To address this, we propose \textbf{RLCSD} (Reinforcement Learning with Contrastive on-policy Self-Distillation), which mitigates this drift by contrasting the teacher-student gap under a correct hint against that under a wrong hint, suppressing the style shift that conditioning on a hint tends to induce regardless of correctness, and yielding a signal that is more concentrated on task-bearing tokens. Experiments on Qwen3 (1.7B/4B/8B) and Olmo-3-7B-Think across mathematical and logical reasoning show that RLCSD consistently outperforms GRPO and prior OPSD methods. We further show that the contrastive principle is general: it plugs into existing OPSD methods to improve them, and its underlying insight extends to the broader cross-model on-policy distillation setting.

📄 PDF Abstract BibTeX arXiv:2606.11709

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningLogical Reasoning

Similar Papers 제목 키워드 기반

Contrastive Reinforced Policy Optimization via Privileged Self-Distillation

2026-07-30 · Xingjian Wu, Junlin Liu, Xingchen Liu, Xuhang Zhu 외 arxiv

Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD). While OPSD provides dense, logit-level super…

Reinforcement LearningContrastive Learning

Self-Distilled Policy Gradient

2026-06-02 · Yifeng Liu, Shiyuan Zhang, Yifan Zhang, Quanquan Gu arxiv

On-policy self-distillation, where a language model conditions on privileged context to supervise its own generations, is a promising source of dense supervision for sparse-reward reinforcement learning. Actually, it can…

Reinforcement Learning

Visual Contrastive Self-Distillation

2026-07-23 · Yijun Liang, Yunjie Tian, Yijiang Li, Yuqi Jia 외 arxiv

On-policy self-distillation (OPSD) is promising as it removes the external teacher required by on-policy distillation (OPD), yet it still needs asymmetric information between teacher and student to ensure that the self-t…

From Generic Correlation to Input-Specific Credit in On-Policy Self Distillation

2026-05-12 · Guobin Shen, Lei Huang, Xiang Cheng, Chenxiao Zhao 외 arxiv

On-policy self-distillation has emerged as a promising paradigm for post-training language models, in which the model conditions on environment feedback to serve as its own teacher, providing dense token-level rewards wi…

Contrastive Distillation Is a Sample-Efficient Self-Supervised Loss Policy for Transfer Learning

2022-12-21 · Chris Lengerich, Gabriel Synnaeve, Amy Zhang, Hugh Leather 외

Traditional approaches to RL have focused on learning decision policies directly from episodic decisions, while slowly and implicitly learning the semantics of compositional representations needed for generalization. Whi…

Few-Shot LearningLanguage ModellingSelf-LearningTransfer Learning