Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation

• URL: http://arxiv.org/abs/2606.18844v1
• Date: Wed, 17 Jun 2026 09:24:19 GMT
• Title: Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
• Abstract summary: 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.
• Score: 14.043179860831406
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution. However, because this supervision is generated via uncontrolled sampling, it provides no diagnostic insight into the model's specific errors or corrective guidance for its individual failure patterns. Consequently, the model learns to imitate a privileged distribution rather than receiving fine-grained corrections that pinpoint where and why its reasoning fails. In this paper, we propose Trajectory-Augmented Policy Optimization (TAPO), which advances self-distillation from implicit distributional alignment to explicit trajectory construction. During RL training, the model produces both correct and incorrect rollouts to the same query, and TAPO leverages this contrastive structure to construct micro-reflective corrections, new training trajectories that retain the model's erroneous reasoning up to the point of failure, then insert a natural-language diagnosis and corrected reasoning guided by a correct reference from the same sampling group. Since each trajectory is anchored in the learner's own prefix and solutions, the corrective signal preserves the model's on-policy distribution to a greater extent than the position-wise alignment imposed by KL-based methods. To integrate these trajectories, TAPO introduces difficulty-aware candidate selection at the model's capability boundary and decoupled advantage estimation to prevent gradient contamination. Experiments on AIME 2024, AIME 2025, and HMMT 2025 show that TAPO achieves consistent improvements over GRPO under the same number of training steps. Further analysis demonstrates that TAPO strengthens both first-pass reasoning and error-correction effectiveness.

Related papers

• FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience [18.64380706071327]
  FlowBalance is a verifier-grounded self-improvement method that learns a normalized distribution over complete responses.<n>For each on-policy trajectory, a frozen training-time view of the same policy uses privileged context to produce token-level log-probability gains.<n>Our analysis establishes within-group contrast preservation, a minimum-change reverse-KL characterization, monotonic verifier control of target reward, and an exact correction against false-positive self-guidance on rejected responses.
  arXiv  Detail & Related papers  (2026-09-03T00:47:11Z)
• 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)
• RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation [46.554172283247915]
  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.
  arXiv  Detail & Related papers  (2026-06-10T06:31:59Z)
• MixSD: Mixed Contextual Self-Distillation for Knowledge Injection [29.7616760417696]
  Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models.<n>We argue this forgetting arises because fine-tuning targets from humans or external systems diverge from the model's autoregressive distribution.<n>We propose MixSD, a simple external-teacher-free method for distribution-aligned knowledge injection.
  arXiv  Detail & Related papers  (2026-05-16T07:57:09Z)
• Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models [65.89572755202245]
  Diffusion Language Models (DLMs) offer stronger global awareness and highly parallel generation.<n>Post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient.<n>We propose a self-distilled trajectory-based post-training framework that aligns training with the easy-to-hard structure of inference.
  arXiv  Detail & Related papers  (2026-05-12T09:39:06Z)
• The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation [67.26315138466312]
  We propose a calibration-aware OPD framework, CaOPD, that estimates empirical confidence from model rollouts.<n>Our findings highlight that capability distillation does not imply confidence, and that confidence should be treated as an essential objective in post-training.
  arXiv  Detail & Related papers  (2026-04-18T04:43:40Z)
• InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning [32.274434679047395]
  Outcome-reward reinforcement learning (RL) has proven effective at improving the reasoning capabilities of large language models (LLMs)<n>Standard RL assigns credit only at the level of the final answer, penalizing entire reasoning traces when the outcome is incorrect.<n>We introduce Intervention Training (InT), a training paradigm in which the model performs fine-grained credit assignment on its own reasoning traces.
  arXiv  Detail & Related papers  (2026-01-20T18:15:38Z)
• Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity [13.211627219720796]
  Reinforcement Learning (RL) has become the de facto standard for tuning LLMs to solve tasks involving reasoning.<n>We argue that RL implicitly optimize the "mode-seeking" or "zero-forcing" Reverse KL to a target distribution causing the model to concentrate mass on certain high-probability regions of the target while others.<n>In this work, we instead begin from an explicit target distribution, obtained by filtering out incorrect answers while neglecting the relative probabilities of correct ones.
  arXiv  Detail & Related papers  (2025-12-05T18:56:40Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Training Language Models to Self-Correct via Reinforcement Learning [98.35197671595343]
  Self-correction has been found to be largely ineffective in modern large language models (LLMs) We develop a multi-turn online reinforcement learning approach, SCoRe, that significantly improves an LLM's self-correction ability using entirely self-generated data. We find that SCoRe achieves state-of-the-art self-correction performance, improving the base models' self-correction by 15.6% and 9.1% respectively on MATH and HumanEval.
  arXiv  Detail & Related papers  (2024-09-19T17:16:21Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)

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.