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

• URL: http://arxiv.org/abs/2606.11709v1
• Date: Wed, 10 Jun 2026 06:31:59 GMT
• Title: RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation
• Abstract summary: On-policy self-distillation provides dense, token-level supervision for reasoning models.<n>We show that the learning signal drawn from this distributional gap concentrates on style tokens rather than task-bearing ones.<n>We propose textbfRLCSD (Reinforcement Learning with Contrastive on-policy Self-Distillation) to mitigate this drift.
• Score: 46.554172283247915
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Contrastive On-Policy Distillation [36.47487086937924]
  We propose COPD, a contrastive On-policy Distillation framework.<n> COPD directly encourages the student model to learn more concise and efficient reasoning strategies.
  arXiv  Detail & Related papers  (2026-07-21T12:35:04Z)
• dOPSD: On-Policy Self-Distillation for Diffusion Language Models [52.60302464420127]
  Diffusion large language models generate text by iteratively denoising a masked sequence.<n>Supervised fine-tuning is off-policy and suffers from exposure bias, while reinforcement learning gives only sparse, sequence-level rewards.<n>On-policy self-distillation (OPSD) offers a promising alternative, using one model as both student and teacher.
  arXiv  Detail & Related papers  (2026-07-05T17:47:29Z)
• Purified OPSD: On-Policy Self-Distillation Without Losing How to Think [52.879387744920415]
  We find that on-policy self-distillation (OPSD) consistently fails on long chain-of-thought (long-CoT) reasoning models.<n>We propose a two-step solution: first, we construct a reference-only teacher to isolate the non-transferable component of the supervision signal.<n>Second, we use pointwise mutual information (PMI) as the mechanism to transform this residual into a well-formed PMI target distribution.
  arXiv  Detail & Related papers  (2026-07-02T14:33:07Z)
• Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation [14.043179860831406]
  Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal.<n>We propose Trajectory-Augmented Policy Optimization (TAPO), which advances self-distillation from implicit distributional alignment to explicit trajectory construction.
  arXiv  Detail & Related papers  (2026-06-17T09:24:19Z)
• Robust Reasoning via Dynamic Token Selection for Distribution-Aligned Self-Distillation [10.71966126081564]
  Self-distillation improves learning efficiency by rewriting reference answers as training data that better matches the model's own distribution.<n>But reference answers also introduce strong stylistic biases, causing the generative model to imitate surface forms rather than learn useful reasoning patterns.<n>We propose Distribution-Aligned Self-Distillation (DASD), which uses an answer-aware reference model to generate candidate tokens and dynamically filters them according to the base model's confidence.
  arXiv  Detail & Related papers  (2026-05-30T09:03:03Z)
• Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning [41.384652481442735]
  We propose textbfDirection-Adaptive Self-Distillation (textbfDASD), which reframes privileged self-distillation from uniform teacher imitation into entropy-routed directional supervision.<n>Across six mathematical reasoning benchmarks, DASD achieves the best macro Avg@16 over strong RLVR and self-distillation baselines.
  arXiv  Detail & Related papers  (2026-05-21T10:07:46Z)
• DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models [55.01951088768769]
  DiffusionOPD is a new multi-task training paradigm for diffusion models based on Online Policy Distillation (OPD)<n>We show that DiffusionOPD consistently surpasses both multi-reward RL and cascade RL baselines in training efficiency and final performance.
  arXiv  Detail & Related papers  (2026-05-14T16:49:09Z)
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data [55.84428098924793]
  We propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration.<n>We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance.<n> Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO.
  arXiv  Detail & Related papers  (2026-04-20T16:43:28Z)
• Self-Distilled RLVR [57.37526213765131]
  We show that learning signals solely derived from the privileged teacher result in severe information leakage and unstable long-term training.<n>We propose textbfRLSD (textbfRLVR with textbfSelf-textbfDistillation)<n>This enables RLSD to simultaneously harness the strengths of both RLVR and OPSD, achieving a higher convergence ceiling and superior training stability.
  arXiv  Detail & Related papers  (2026-04-03T15:50:07Z)
• Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes [31.95045602299568]
  On-policy distillation (OPD) is appealing for large language model (LLM) post-training because it evaluates teacher feedback on student-generated rollouts rather than fixed teacher traces.<n>We revisit OPD from the estimator and implementation sides.<n>We identify three failure modes of sampled-token OPD: an imbalanced one-token signal, unreliable teacher guidance on student-generated prefixes, and distortions caused by tokenizer or special-token mismatch.
  arXiv  Detail & Related papers  (2026-03-26T15:35:59Z)
• Hindsight-Anchored Policy Optimization: Turning Failure into Feedback in Sparse Reward Settings [7.554296968064274]
  We present Hindsight-Anchored Policy optimization (HAPO) for Reinforcement Learning with Verifiable Rewards (RLVR)<n>HAPO employs a hindsight mechanism that selectively anchors optimization to teacher demonstrations during failure.<n>We show that HAPO achieves textitasymptotic consistency: by naturally annealing the teacher signal as the policy improves, HAPO recovers the unbiased on-policy gradient.
  arXiv  Detail & Related papers  (2026-03-11T21:33:41Z)
• Stable On-Policy Distillation through Adaptive Target Reformulation [7.361248172930405]
  Veto is an objective-level reformulation that constructs a geometric bridge in the logit space.<n>Veto consistently outperforms supervised fine-tuning and existing on-policy baselines.
  arXiv  Detail & Related papers  (2026-01-12T02:57:39Z)
• Learning a Diffusion Model Policy from Rewards via Q-Score Matching [93.0191910132874]
  We present a theoretical framework linking the structure of diffusion model policies to a learned Q-function.<n>We propose a new policy update method from this theory, which we denote Q-score matching.
  arXiv  Detail & Related papers  (2023-12-18T23:31:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.