Metacognition in LLMs: Foundations, Progress, and Opportunities
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 t
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 55%Productive-Superintelligence/lllm →
- PossiblePossibly related (embedding) · 53%digiteinfotech/kairon →
- PossiblePossibly related (embedding) · 51%owainlewis/awesome-artificial-intelligence →
- PossiblePossibly related (embedding) · 51%letta-ai/letta →
- PossiblePossibly related (embedding) · 51%KerberosClaw/kc_ai_skills →
- LinkedLinked via arxiv author · 85%Gabrielle Kaili-May Liu →
“Metacognition in LLMs: Foundations, Progress, and Opportunities”
- LinkedLinked via arxiv author · 85%Areeb Gani →
“Metacognition in LLMs: Foundations, Progress, and Opportunities”
- LinkedLinked via arxiv author · 85%Jacqueline Lu →
“Metacognition in LLMs: Foundations, Progress, and Opportunities”