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

2026-04-19

AI Summary

This work addresses the limitations of existing meta-reasoning approaches, which are typically single-episode and event-driven, lacking mechanisms for accumulating metacognitive skills across instances—leading to repeated failures and high cognitive overhead. To overcome this, the paper introduces a Metacognitive Consolidation framework that decouples reasoning, monitoring, and control roles to generate traceable meta-level trajectories. By integrating these trajectories through a hierarchical, multi-timescale mechanism, the framework consolidates experiences into continuously evolving metaknowledge. This approach enables, for the first time, the accumulation and reuse of metacognitive experience across tasks, thereby establishing a meta-reasoning system capable of sustained self-improvement. Empirical results demonstrate consistent performance gains across multiple benchmarks and backbone models, with reasoning capabilities progressively enhancing as metacognitive experience accumulates.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Knowledge Representation and Reasoning: Reasoning with Beliefs

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• meta-reasoning
• metacognitive consolidation
• large language models
• reusable meta-reasoning skills
• reasoning improvement

Innovation

• Metacognitive Consolidation
• meta-reasoning
• reusable meta-knowledge
• hierarchical update mechanism
• self-improving LLMs