Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning

• URL: http://arxiv.org/abs/2604.17399v1
• Date: Sun, 19 Apr 2026 12:02:30 GMT
• Title: Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
• Abstract summary: Large language models (LLMs) have demonstrated strong reasoning capabilities.<n>Increasing attention has shifted toward meta-reasoning as a promising direction for further improvement.<n>We introduce Metacognitive Consolidation, a novel framework in which a model consolidates metacognitive experience into reusable knowledge.
• Score: 42.534586884018076
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities, and as existing approaches for enhancing LLM reasoning continue to mature, increasing attention has shifted toward meta-reasoning as a promising direction for further improvement. However, most existing meta-reasoning methods remain episodic: they focus on executing complex meta-reasoning routines within individual instances, but ignore the accumulation of reusable meta-reasoning skills across instances, leading to recurring failure modes and repeatedly high metacognitive effort. In this paper, we introduce Metacognitive Consolidation, a novel framework in which a model consolidates metacognitive experience from past reasoning episodes into reusable knowledge that improves future meta-reasoning. We instantiate this framework by structuring instance-level problem solving into distinct roles for reasoning, monitoring, and control to generate rich, attributable meta-level traces. These traces are then consolidated through a hierarchical, multi-timescale update mechanism that gradually forms evolving meta-knowledge. Experimental results demonstrate consistent performance gains across benchmarks and backbone models, and show that performance improves as metacognitive experience accumulates over time.

Related papers

• Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs [60.80435138270317]
  We apply reinforcement learning with metacognitive feedback to the problem of faithful calibration.<n>Experiments show RLMF achieves generalizable, state-of-the-art FC on diverse tasks.<n> RLMF surpasses standard RL by up to 63% while enhancing models' ability to assess and express their own capability limits.
  arXiv  Detail & Related papers  (2026-06-30T17:56:01Z)
• MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution [49.24192816558635]
  Large language models (LLMs) exhibit strong reasoning capabilities, yet most LLM-based agents are unable to improve through task interactions.<n>Existing experience-driven methods often rely on memory or executors without enhancing the model's ability to learn.<n>We propose MetaEvo, a two-stage framework for continual agent evolution.
  arXiv  Detail & Related papers  (2026-05-29T09:31:39Z)
• Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning [57.10440766103372]
  Trajectory Regularized Merging (TRM) is a framework that reformulates the merging phase as an optimization process within an augmented trajectory subspace.<n>Our framework integrates three synergistic objectives including task alignment, prediction consistency, and gradient responsiveness to concurrently preserve merged model's historical stability and re-activate optimization dynamics.
  arXiv  Detail & Related papers  (2026-05-08T14:07:32Z)
• Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning [38.92106966820126]
  Recent Vision-Language Models (VLMs) exhibit strong perceptual reasoning abilities, yet they often struggle to adapt efficiently when encountering novel tasks at test time.<n>In contrast, humans leverage the metacognitive model with memory, enabling continuous strategy refinement through metacognitive control when faced with new challenges.<n>We propose metacognitive test-time reasoning (MCTR), a framework that equips models with the ability to learn, adapt, and improve during test time through metacognitive self-updating.
  arXiv  Detail & Related papers  (2025-11-28T15:15:47Z)
• Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs [71.8547241246169]
  We introduce CogEdit, a novel benchmark designed to evaluate MLLMs' meta-cognitive knowledge editing abilities.<n>We propose MIND, a framework that constructs a meta-knowledge memory for self-awareness, employs game-theoretic interactions to monitor knowledge activation, and incorporates label refinement for noise-robust updates.
  arXiv  Detail & Related papers  (2025-09-06T13:26:04Z)
• Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition [89.50068130832635]
  Self-Improving cognition (SIcog) is a self-learning framework for constructing next-generation foundation MLLMs by multimodal knowledge.<n>We propose Chain-of-Description for step-by-step visual understanding and integrate structured Chain-of-Thought (CoT) reasoning to support in-depth multimodal reasoning.<n>Experiments demonstrate SIcog's effectiveness in developing MLLMs with enhanced multimodal cognition.
  arXiv  Detail & Related papers  (2025-03-16T00:25:13Z)
• ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning [53.817538122688944]
  We introduce Reinforced Meta-thinking Agents (ReMA) to elicit meta-thinking behaviors from Reasoning of Large Language Models (LLMs)<n>ReMA decouples the reasoning process into two hierarchical agents: a high-level meta-thinking agent responsible for generating strategic oversight and plans, and a low-level reasoning agent for detailed executions.<n> Empirical results from single-turn experiments demonstrate that ReMA outperforms single-agent RL baselines on complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-12T16:05:31Z)
• Metacognitive Retrieval-Augmented Large Language Models [43.57020180706832]
  This paper introduces MetaRAG, an approach that combines the retrieval-augmented generation process with metacognition. By integrating this, MetaRAG enables the model to monitor, evaluate, and plan its response strategies. Empirical evaluations show that MetaRAG significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2024-02-18T15:41:31Z)
• Understanding Benign Overfitting in Nested Meta Learning [44.08080315581763]
  We focus on the meta learning settings with a challenging nested structure that we term the nested meta learning. Our theory contributes to understanding the delicate interplay among data heterogeneity, model adaptation and benign overfitting in nested meta learning tasks.
  arXiv  Detail & Related papers  (2022-06-27T17:46:57Z)

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.