Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models

• URL: http://arxiv.org/abs/2602.10224v1
• Date: Tue, 10 Feb 2026 19:16:09 GMT
• Title: Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models
• Authors: Shiting Huang, Zecheng Li, Yu Zeng, Qingnan Ren, Zhen Fang, Qisheng Su, Kou Shi, Lin Chen, Zehui Chen, Feng Zhao,
• Abstract summary: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for enhancing the reasoning capabilities of Large Language Models (LLMs)<n>We propose Meta-Experience Learning (MEL), a novel framework that incorporates self-distilled meta-experience into the model's parametric memory.<n>MEL achieves consistent improvements on benchmarks, yielding 3.92%--4.73% Pass@1 gains across varying model sizes.
• Score: 28.300560850867374
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for enhancing the reasoning capabilities of Large Language Models (LLMs). Despite its efficacy, RLVR faces a meta-learning bottleneck: it lacks mechanisms for error attribution and experience internalization intrinsic to the human learning cycle beyond practice and verification, thereby limiting fine-grained credit assignment and reusable knowledge formation. We term such reusable knowledge representations derived from past errors as meta-experience. Based on this insight, we propose Meta-Experience Learning (MEL), a novel framework that incorporates self-distilled meta-experience into the model's parametric memory. Building upon standard RLVR, we introduce an additional design that leverages the LLM's self-verification capability to conduct contrastive analysis on paired correct and incorrect trajectories, identify the precise bifurcation points where reasoning errors arise, and summarize them into generalizable meta-experience. The meta-experience is further internalized into the LLM's parametric memory by minimizing the negative log-likelihood, which induces a language-modeled reward signal that bridges correct and incorrect reasoning trajectories and facilitates effective knowledge reuse. Experimental results demonstrate that MEL achieves consistent improvements on benchmarks, yielding 3.92%--4.73% Pass@1 gains across varying model sizes.

Related papers

• Learning Wisdom from Errors: Promoting LLM's Continual Relation Learning through Exploiting Error Cases [6.580051318980816]
  We propose an instruction-based continual contrastive tuning approach for Large Language Models (LLMs) in CRE.<n>We experimentally evaluate our model on TACRED and FewRel, and the results show that our model achieves new state-of-the-art CRE performance with significant improvements.
  arXiv  Detail & Related papers  (2025-08-16T12:49:11Z)
• TRAIL: Joint Inference and Refinement of Knowledge Graphs with Large Language Models [5.678291291711662]
  TRAIL is a novel, unified framework for Thinking, Reasoning, And Incremental Learning.<n>It couples joint inference and dynamic KG refinement with large language models.<n>Extensive experiments on multiple benchmarks demonstrate that TRAIL outperforms existing KG-augmented and retrieval-augmented LLM baselines by 3% to 13%.
  arXiv  Detail & Related papers  (2025-08-06T14:25:05Z)
• Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning [93.00629872970364]
  Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks.<n>We introduce SPARKLE, a fine-grained analytic framework to dissect the effects of RL across three key dimensions.<n>We study whether difficult problems -- those yielding no RL signals and mixed-quality reasoning traces -- can still be effectively used for training.
  arXiv  Detail & Related papers  (2025-06-05T07:53:59Z)
• UniErase: Towards Balanced and Precise Unlearning in Language Models [69.04923022755547]
  Large language models (LLMs) require iterative updates to address the outdated information problem.<n>UniErase is a novel unlearning framework that demonstrates precision and balanced performances between knowledge unlearning and ability retaining.
  arXiv  Detail & Related papers  (2025-05-21T15:53:28Z)
• UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets [41.0340052199534]
  Large Language Models (LLMs) inevitably acquire harmful information during training on massive datasets.<n>Existing unlearning methods focus on forgetting target data while overlooking the crucial impact of logically related knowledge on the effectiveness of unlearning.<n>We propose Unlearning Improvement via Extrapolation (UIPE), a method that removes knowledge highly correlated with the forgetting targets.
  arXiv  Detail & Related papers  (2025-03-06T18:40:00Z)
• ReLearn: Unlearning via Learning for Large Language Models [64.2802606302194]
  We propose ReLearn, a data augmentation and fine-tuning pipeline for effective unlearning.<n>This framework introduces Knowledge Forgetting Rate (KFR) and Knowledge Retention Rate (KRR) to measure knowledge-level preservation.<n>Our experiments show that ReLearn successfully achieves targeted forgetting while preserving high-quality output.
  arXiv  Detail & Related papers  (2025-02-16T16:31:00Z)
• What Do Learning Dynamics Reveal About Generalization in LLM Reasoning? [83.83230167222852]
  We find that a model's generalization behavior can be effectively characterized by a training metric we call pre-memorization train accuracy. By connecting a model's learning behavior to its generalization, pre-memorization train accuracy can guide targeted improvements to training strategies.
  arXiv  Detail & Related papers  (2024-11-12T09:52:40Z)
• Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning [7.803423399566274]
  Large language models (LLMs) trained with Reinforcement Learning from Human Feedback have demonstrated remarkable capabilities, but their underlying reward functions and decision-making processes remain opaque.<n>This paper introduces a novel approach to interpreting LLMs by applying inverse reinforcement learning (IRL) to recover their implicit reward functions.<n>We conduct experiments on toxicity-aligned LLMs of varying sizes, extracting reward models that achieve up to 85% accuracy in predicting human preferences.
  arXiv  Detail & Related papers  (2024-10-16T12:14:25Z)
• Learn To Learn More Precisely [30.825058308218047]
  "Learn to learn more precisely" aims to make the model learn precise target knowledge from data. We propose a simple and effective meta-learning framework named Meta Self-Distillation(MSD) to maximize the consistency of learned knowledge. MSD exhibits remarkable performance in few-shot classification tasks in both standard and augmented scenarios.
  arXiv  Detail & Related papers  (2024-08-08T17:01:26Z)
• LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement [93.38736019287224]
  "LLMs-as-Instructors" framework autonomously enhances the training of smaller target models. Inspired by the theory of "Learning from Errors", this framework employs an instructor LLM to meticulously analyze the specific errors within a target model. Within this framework, we implement two strategies: "Learning from Error," which focuses solely on incorrect responses to tailor training data, and "Learning from Error by Contrast", which uses contrastive learning to analyze both correct and incorrect responses for a deeper understanding of errors.
  arXiv  Detail & Related papers  (2024-06-29T17:16:04Z)
• Towards Effective Evaluations and Comparisons for LLM Unlearning Methods [97.2995389188179]
  This paper seeks to refine the evaluation of machine unlearning for large language models.<n>It addresses two key challenges -- the robustness of evaluation metrics and the trade-offs between competing goals.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Theoretical Characterization of the Generalization Performance of Overfitted Meta-Learning [70.52689048213398]
  This paper studies the performance of overfitted meta-learning under a linear regression model with Gaussian features. We find new and interesting properties that do not exist in single-task linear regression. Our analysis suggests that benign overfitting is more significant and easier to observe when the noise and the diversity/fluctuation of the ground truth of each training task are large.
  arXiv  Detail & Related papers  (2023-04-09T20:36:13Z)

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.