Survey and Roadmap on LLM Metacognition

yale-nlp · hf · 2026-07-14

This is a survey on **LLM metacognition**, aiming to outline the foundations, progress, and opportunities in the field. The authors argue that metacognition is a crucial component of intelligence, vital for learning, problem-solving, decision-making, and communication. However, for LLMs, when, how, and to what extent they can possess or be endowed with metacognitive abilities remains an open question. The article systematically summarizes the current research landscape, including: - **Evaluation Methods & Benchmarks**: How to measure a model's metacognitive capabilities; - **Enhancement & Elicitation Techniques**: How to enable models to exhibit better metacognition; - **Applications & Impact**: How these capabilities improve reliability, transparency, and overall intelligence; - **Open Problems & Challenges**: Promising directions for future research. The authors also provide a curated list of papers for tracking this emerging trend.

Related event: Survey Maps LLM Metacognition and Roadmap(2 posts)→

Original post →

More from Research

Research channel →