arXivPaperNeeds Review

Metacognition in LLMs: Foundations, Progress, and Opportunities

This survey maps how LLMs inspect and regulate their reasoning, giving agent builders a framework for choosing self-checks without assuming introspection is reliable.

arXiv

Open Source Open Markdown Open JSON

Source Summary

This **first comprehensive overview** taxonomizes LLM metacognition: how models monitor and regulate their own reasoning. It covers measurement benchmarks, elicitation and improvement methods, applications, findings, and open research questions.

Practical Implication

Use the taxonomy to separate distinct self-checking needs in an agent: detecting uncertainty, evaluating an intermediate result, and changing course. Match each mechanism to an evaluation rather than treating reflection as one generic capability.

Agent-Ready Context

This **first comprehensive overview** taxonomizes LLM metacognition: how models monitor and regulate their own reasoning. It covers measurement benchmarks, elicitation and improvement methods, applications, findings, and open research questions.

Use the taxonomy to separate distinct self-checking needs in an agent: detecting uncertainty, evaluating an intermediate result, and changing course. Match each mechanism to an evaluation rather than treating reflection as one generic capability.

The survey emphasizes that it remains unclear **when and to what extent** LLMs have effective metacognitive abilities. It organizes existing evidence; it does not establish that self-reports or reflective traces are dependable controls.

Context Map

agentresearch#reasoning#agent-reliability#agent-evals

Uncertainty

The survey emphasizes that it remains unclear **when and to what extent** LLMs have effective metacognitive abilities. It organizes existing evidence; it does not establish that self-reports or reflective traces are dependable controls.