这篇把LLM的自我认知行为串起来了，比如什么时候该停、知道自己不知道啥，对做可靠AI agent的人特别有用。
该综述论文认为，LLM中常见的置信度校准、自我验证、知道何时停止及知道未知等行为实际上是元认知的不同方面。作者提出了一个全面的元认知地图，并分类了评估这些能力的方法与基准（如arxiv:2607.11881）。研究将这些能力与LLM的能力、可靠性和透明度联系起来，指出随着智能体任务周期变长，监控和调节自身推理成为衡量可靠性的重要方式。
Highly-recommended overview of metacognition in LLMs. (bookmark it) Interesting behaviors in LLMs ...
Highly-recommended overview of metacognition in LLMs. (bookmark it) Interesting behaviors in LLMs like confidence calibration, self-verification, knowing when to stop, and knowing what you do not know have mostly been studied in isolation. This survey argues they are facets of one thing, metacognition, and proposes a comprehensive map of it. The authors taxonomize methods and benchmarks for measuring and evaluating metacognitive abilities in LLMs, then connect those abilities to capability, reliability, and transparency. As agents take on longer horizons, the ability to monitor and regulate their own reasoning becomes an important way to measure reliability. Paper: arxiv.org/abs/2607.11881 Learn to build effective AI agents in our academy: academy.dair.ai 💬 7 🔄 2 ❤️ 15 👀 1816 📊 12 ⚡