Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
Southeast University(东南大学);King’s College London(伦敦国王学院);The Alan Turing Institute(艾伦·图灵研究所);Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学(山东科学院))
Ziqing Zhuang, Linhai Zhang, Jiasheng Si, Deyu Zhou, Yulan He
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.
MeLA: A Metacognitive LLM-Driven Architecture for Automatic Heuristic Design
School of Computer Science, University of Nottingham Ningbo China(诺丁汉大学宁波分校计算机科学学院);College of Teacher Education, Zhejiang Normal University(浙江师范大学教师教育学院)
Distilling Metacognitive Behaviors through Agentic Editing
Dept. of ECE Seoul Nat’l Univ.(首尔国立大学电子工程系);AI Center Samsung Elec. Korea(三星电子韩国人工智能中心);AIIS, ASRI, INMC, ISRC, Interdisc. Prog. in AI Seoul Nat’l Univ.(首尔国立大学人工智能研究所、高级研究机构、人工智能中心、国际研究所以及人工智能跨学科研究计划)
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
Department of XXX, University of YYY, Location, Country(XXX部门,YYYY大学,地点,国家);School of ZZZ, Institute of WWW, Location, Country(ZZZ学院,WWW研究所,地点,国家);Inria (Flowers), University of Bordeaux, France(Inria(Flowers),波尔多大学,法国);MIT, Computational Cognitive Science Lab, Cambridge, MA, USA(麻省理工学院,计算认知科学实验室,马萨诸塞州剑桥,美国)
Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach
Arizona State University(亚利桑那州立大学);University of Science and Technology of China(中国科学技术大学);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);MIT(麻省理工学院);Harvard University(哈佛大学)
MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller
Southern University of Science and Technology(南方科技大学);The Hong Kong University of Science and Technology(香港科技大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Tongji University(同济大学)
A Sentiment Consolidation Framework for Meta-Review Generation
School of Computing and Information Systems, The University of Melbourne(墨尔本大学计算与信息系统学院);Language Technologies Institute, Carnegie Mellon University(卡内基梅隆大学语言技术研究所)
Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
Meta;Mila-Quebec AI Institute, University of Montreal(魁北克AI研究所,蒙特利尔大学);Princeton University(普林斯顿大学);Mila--Quebec AI Institute, Université de Montréal(魁北克AI研究所,蒙特利尔大学)
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
Tongji University(同济大学);Shanghai AI Laboratory(上海人工智能实验室);Nanyang Technological University(南洋理工大学);University of Science and Technology of China(中国科学技术大学);EPFL(苏黎世联邦理工学院);Wuhan University(武汉大学)
Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence
City University of Hong Kong(香港城市大学);East China Normal University(华东师范大学);University of Electronic Science and Technology of China(电子科技大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));The University of Hong Kong(香港大学)
Position: Artificial Intelligence Needs Meta Intelligence -- the Case for Metacognitive AI
University of Texas Rio Grande Valley, Edinburg, TX, USA(德克萨斯大学里奥格兰德谷分校);Rochester Institute of Technology, Rochester, NY, USA(罗切斯特理工学院);Syracuse University, Syracuse, NY, USA(锡拉库萨大学)
MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs
School of Computer Science and Technology, East China Normal University(东华大学计算机科学与技术学院);Shanghai AI Lab, Shanghai Innovation Institute(上海人工智能实验室,上海创新研究院)
Enhancing Metacognitive AI: Knowledge-Graph Population with Graph-Theoretic LLM Enrichment
Department of Cognitive Science, Carleton University(认知科学系,卡尔顿大学);Faculty of Computer and Information Science, Ben-Gurion University of the Negev(计算机与信息科学学院,贝内-约尔大学)
Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction
Temple University(天普大学);University of Central Florida(中佛罗里达大学);Arizona State University(亚利桑那州立大学);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);Honda Research Institute USA(本田美国研究院)
CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning
Nanyang Technological University(南洋理工大学);Carnegie Mellon University(卡内基梅隆大学);Zhejiang University(浙江大学);Sun Yat-Sen University(中山大学);National University of Singapore(新加坡国立大学);Fudan University(复旦大学);City University of Hong Kong (Dongguan)(香港城市大学(东莞));Zhejiang Lab(之江实验室)