mlsanityData to 7 Oct 2026

Metacognitive AI: Framework and the Case for a Neurosymbolic Approach

arXiv 2406.12147 ↗First posted 17 Jun 2024cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Metacognition is the concept of reasoning about an agent's own internal processes and was originally introduced in the field of developmental psychology. In this position paper, we examine the concept of applying metacognition to artificial intelligence. We introduce a framework for understanding metacognitive artificial intelligence (AI) that we call TRAP: transparency, reasoning, adaptation, and perception. We discuss each of these aspects in-turn and explore how neurosymbolic AI (NSAI) can be leveraged to address challenges of metacognition.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 13 of its 37 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

13 of 37 references.

References · 13

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  2. 2017Hindsight Experience Replaycited by 1,096
  3. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 401
  4. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 267
  5. 2020Neurosymbolic AI: The 3rd Wavecited by 253
  6. 2017Learning Explanatory Rules from Noisy Datacited by 210
  7. 2020Logic Tensor Networkscited by 197
  8. 2020Coherent Hierarchical Multi-Label Classification Networkscited by 65
  9. 2022Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learningcited by 27
  10. 2024Uncertainty Regularized Evidential Regressioncited by 13
  11. 2023The Roles of Symbols in Neural-based AI: They are Not What You Think!cited by 4
  12. 2023Uncertainty-aware Grounded Action Transformation towards Sim-to-Real Transfer for Traffic Signal Controlcited by 3
1 more
  1. 2023Explaining Deep Learning Hidden Neuron Activations using Concept Inductioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 4.

9 papers.

  1. 2025A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Modelscited by 36
  2. 2025Truly Self-Improving Agents Require Intrinsic Metacognitive Learningcited by 13
  3. 2025Identifying Features that Shape Perceived Consciousness in Large Language Model-based AI: A Quantitative Study of Human Responsescited by 3
  4. 2025Probabilistic Foundations for Metacognition via Hybrid-AIcited by 1
  5. 2026Metacognition in LLMs: Foundations, Progress, and Opportunitiescited by 1
  6. 2025Abduction of Domain Relationships from Data for VQAcited by 0
  7. 2026Agentic AI for Cybersecurity: A Meta-Cognitive Architecture for Governable Autonomycited by 0
  8. 2026Position: Artificial Intelligence Needs Meta Intelligence -- the Case for Metacognitive AIcited by 0
  9. 2026ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learningcited by 0