mlsanityData to 7 Oct 2026

Metacognition is all you need? Using Introspection in Generative Agents to Improve Goal-directed Behavior

arXiv 2401.10910 ↗First posted 9 Jan 2024q-bio.NC cs.AIcited by 15

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Recent advances in Large Language Models (LLMs) have shown impressive capabilities in various applications, yet LLMs face challenges such as limited context windows and difficulties in generalization. In this paper, we introduce a metacognition module for generative agents, enabling them to observe their own thought processes and actions. This metacognitive approach, designed to emulate System 1 and System 2 cognitive processes, allows agents to significantly enhance their performance by modifying their strategy. We tested the metacognition module on a variety of scenarios, including a situation where generative agents must survive a zombie apocalypse, and observe that our system outperform others, while agents adapt and improve their strategies to complete tasks over time.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 19 of its 32 references that are in the map. First posted on arXiv 9 Jan 2024.

Builds on

19 of 32 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  7. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  8. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  9. 2023Mistral 7Bcited by 3,065
  10. 2024Mixtral of Expertscited by 1,785
  11. 2024TinyLlama: An Open-Source Small Language Modelcited by 604
  12. 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 559
7 more
  1. 2023PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPUcited by 210
  2. 2023SILO Language Models: Isolating Legal Risk In a Nonparametric Datastorecited by 71
  3. 2021Relating transformers to models and neural representations of the hippocampal formationcited by 62
  4. 2021Grid Cell Path Integration For Movement-Based Visual Object Recognitioncited by 5
  5. 2021Assured Learning-enabled Autonomy: A Metacognitive Reinforcement Learning Frameworkcited by 3
  6. 2022Computational Metacognitioncited by 3
  7. 2022Grid cells and their potential application in AIcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 4; 2026: 3.

15 papers.

Sort:

By area:

  1. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 140
  2. 2024The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Modelscited by 62
  3. 2024Self-Reflection in LLM Agents: Effects on Problem-Solving Performancecited by 38
  4. 2025Large language models for artificial general intelligence (AGI): A survey of foundational principles and approachescited by 18
  5. 2024Training Language Models to Critique With Multi-agent Feedbackcited by 16
  6. 2024Imagining and building wise machines: The centrality of AI metacognitioncited by 12
  7. 2024PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Gamescited by 10
  8. 2024Can Agents Spontaneously Form a Society? Introducing a Novel Architecture for Generative Multi-Agents to Elicit Social Emergencecited by 5
  9. 2025Adapting Like Humans: A Metacognitive Agent with Test-time Reasoningcited by 4
  10. 2026Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMscited by 4
  11. 2024ITCMA: A Generative Agent Based on a Computational Consciousness Structurecited by 3
  12. 2025Static Sandboxes Are Inadequate: Modeling Societal Complexity Requires Open-Ended Co-Evolution in LLM-Based Multi-Agent Simulationscited by 2
3 more
  1. 2026Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimizationcited by 2
  2. 2026Metacognition in LLMs: Foundations, Progress, and Opportunitiescited by 1
  3. 2025From Mimicry to True Intelligence (TI) -- A New Paradigm for Artificial General Intelligencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Competence-Aware AI Agents with Metacognition for Unknown Situations and Environments (MUSE)
  2. 2025Truly Self-Improving Agents Require Intrinsic Metacognitive Learning
  3. 2026MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation
  4. 2026Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement
  5. 2025Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey
  6. 2026MIRROR: A Hierarchical Benchmark for Metacognitive Calibration in Large Language Models
  7. 2024Generative AI as a metacognitive agent: A comparative mixed-method study with human participants on ICF-mimicking exam performance
  8. 2026MetaMind: General and Cognitive World Models in Multi-Agent Systems by Meta-Theory of Mind