Metacognition in LLMs: Foundations, Progress, and Opportunities

• URL: http://arxiv.org/abs/2607.11881v1
• Date: Mon, 13 Jul 2026 17:58:37 GMT
• Title: Metacognition in LLMs: Foundations, Progress, and Opportunities
• Abstract summary: Metacognition is a foundational component of intelligence critical to effective learning, problem solving, decision-making, communication, and more.<n>This paper bridges the gap by presenting the first comprehensive overview of the current state of knowledge on metacognition for LLMs.<n>We analyze and taxonomize the landscape of this emerging field and summarize recent technical advancements.
• Score: 37.62374107119116
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Metacognition is a foundational component of intelligence critical to effective learning, problem solving, decision-making, communication, and more. In recent years, it has become increasingly recognized as a cornerstone of capable, transparent AI systems. Yet while LLMs have made significant progress across diverse real-world tasks, it is not yet clear when, how, or to what extent they can exhibit or be endowed with effective metacognitive abilities, nor how such abilities can be adapted to advance the fundamental capabilities, reliability, and intelligence of AI systems. This paper bridges this gap by presenting the first comprehensive overview of the current state of knowledge on metacognition for LLMs. We analyze and taxonomize the landscape of this emerging field and summarize recent technical advancements, including methods and benchmarks to measure and evaluate LLMs' metacognitive abilities, techniques to elicit, improve, and apply metacognition in LLMs, and findings and implications of ongoing research. We also discuss applications, open questions and challenges, and promising directions for future work. Our aim is to provide a detailed and up-to-date review of this topic and stimulate meaningful research and discussion. An organized list of papers can be found at https://github.com/yale-nlp/LLM-Metacognition.

Related papers

• LLMs4All: A Systematic Review of Large Language Models Across Academic Disciplines [60.559790988113775]
  Large Language Models (LLMs) based applications such as ChatGPT have shown the capability of generating human-like conversation.<n>This paper will offer an overview of state-of-the-art LLMs and their integration into a wide range of academic disciplines.
  arXiv  Detail & Related papers  (2025-09-23T21:09:24Z)
• Advances in LLMs with Focus on Reasoning, Adaptability, Efficiency and Ethics [0.46174569259495524]
  This survey paper outlines the key developments in the field of Large Language Models (LLMs)<n>The techniques that have been most effective in bridging the gap between human and machine communications include the Chain-of-Thought prompting, Instruction Tuning, and Reinforcement Learning from Human Feedback.<n>A significant focus is placed on efficiency, detailing scaling strategies, optimization techniques, and the influential Mixture-of-Experts (MoE) architecture.
  arXiv  Detail & Related papers  (2025-06-14T05:55:19Z)
• Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes [84.1059652774853]
  Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in general vision-language tasks.<n>Recent studies have exposed critical limitations in their spatial reasoning capabilities.<n>This deficiency in spatial reasoning significantly constrains MLLMs' ability to interact effectively with the physical world.
  arXiv  Detail & Related papers  (2025-04-21T11:48:39Z)
• Metacognition and Uncertainty Communication in Humans and Large Language Models [2.3419031955865517]
  Large language models (LLMs) are increasingly embedded in both high-stakes and widespread low-stakes contexts.<n>We show that while humans and LLMs can sometimes appear quite aligned in their metacognitive capacities and behaviors, it is clear many differences remain.<n>We discuss how endowing future LLMs with more sensitive and more calibrated metacognition may also help them develop new capacities such as more efficient learning, self-direction, and curiosity.
  arXiv  Detail & Related papers  (2025-04-18T19:24:17Z)
• A Comprehensive Survey on Integrating Large Language Models with Knowledge-Based Methods [4.686190098233778]
  Large Language Models (LLMs) can be integrated with structured knowledge-based systems.<n>This article surveys the relationship between LLMs and knowledge bases, looks at how they can be applied in practice, and discusses related technical, operational, and ethical challenges.<n>It demonstrates the merits of incorporating generative AI into structured knowledge-base systems concerning data contextualization, model accuracy, and utilization of knowledge resources.
  arXiv  Detail & Related papers  (2025-01-19T23:25:21Z)
• Decoding Large-Language Models: A Systematic Overview of Socio-Technical Impacts, Constraints, and Emerging Questions [1.1970409518725493]
  The article highlights the application areas that could have a positive impact on society along with the ethical considerations. It includes responsible development considerations, algorithmic improvements, ethical challenges, and societal implications.
  arXiv  Detail & Related papers  (2024-09-25T14:36:30Z)
• Knowledge Mechanisms in Large Language Models: A Survey and Perspective [88.51320482620679]
  This paper reviews knowledge mechanism analysis from a novel taxonomy including knowledge utilization and evolution.<n>We discuss what knowledge LLMs have learned, the reasons for the fragility of parametric knowledge, and the potential dark knowledge (hypothesis) that will be challenging to address.
  arXiv  Detail & Related papers  (2024-07-22T06:15:59Z)
• A Survey on Symbolic Knowledge Distillation of Large Language Models [8.237773729114926]
  Survey focuses on the emerging and critical area of symbolic knowledge distillation in Large Language Models. Describes the core challenges, including maintaining the depth of knowledge in a comprehensible format. Examines the various approaches and techniques that have been developed in this field.
  arXiv  Detail & Related papers  (2024-07-12T12:18:19Z)
• FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition [56.76951887823882]
  Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks. We present FAC$2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
  arXiv  Detail & Related papers  (2024-02-29T21:05:37Z)
• Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation [109.8527403904657]
  We show that large language models (LLMs) possess unwavering confidence in their knowledge and cannot handle the conflict between internal and external knowledge well. Retrieval augmentation proves to be an effective approach in enhancing LLMs' awareness of knowledge boundaries. We propose a simple method to dynamically utilize supporting documents with our judgement strategy.
  arXiv  Detail & Related papers  (2023-07-20T16:46:10Z)

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.