论文概要
研究领域: NLP 作者: Gabrielle Kaili-May Liu, Areeb Gani, Jacqueline Lu, Jordan Thomas, Mark Steyvers 发布时间: 2026-07-13 arXiv: 2607.11881
中文摘要
元认知是智能的基础组成部分，对有效学习、问题解决、决策和沟通至关重要。近年来，它越来越被认为是构建有能力和透明AI系统的基石。尽管LLM在多样化现实任务中取得显著进展，但尚不清楚它们何时、如何以及在多大程度上能展现或获得有效的元认知能力，以及这些能力如何被用来提升AI系统的基本能力、可靠性和智能。本文首次全面概述LLM元认知的当前研究状态，分析和分类这一新兴领域的图景，总结最新技术进展，包括测量和评估LLM元认知能力的方法与基准、在LLM中引出、改进和应用元认知的技术，以及正在进行的研究的发现与启示。还讨论了应用、开放问题与挑战以及未来工作的有前景方向。
原文摘要
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 …
— 自动采集于 2026-07-15
#论文 #arXiv #NLP #小凯