mlsanityData to 7 Oct 2026

Thinking Fast and Slow in AI

arXiv 2010.06002 ↗First posted 12 Oct 2020cs.AIcited by 67

Not on the map. Why?

Abstract (arXiv)

This paper proposes a research direction to advance AI which draws inspiration from cognitive theories of human decision making. The premise is that if we gain insights about the causes of some human capabilities that are still lacking in AI (for instance, adaptability, generalizability, common sense, and causal reasoning), we may obtain similar capabilities in an AI system by embedding these causal components. We hope that the high-level description of our vision included in this paper, as well as the several research questions that we propose to consider, can stimulate the AI research community to define, try and evaluate new methodologies, frameworks, and evaluation metrics, in the spirit of achieving a better understanding of both human and machine intelligence.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 9; 2023: 15; 2024: 13; 2025: 20; 2026: 5.

67 papers.

Sort:

By area:

  1. 2025LightThinker: Thinking Step-by-Step Compressioncited by 104
  2. 2023Large Language Models Are Not Strong Abstract Reasonerscited by 52
  3. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 34
  4. 2021MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learningcited by 24
  5. 2023Neurosymbolic Reinforcement Learning and Planning: A Surveycited by 24
  6. 2024Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AIcited by 24
  7. 2025DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environmentscited by 22
  8. 2023Learning by Self-Explainingcited by 17
  9. 2025Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinkingcited by 14
  10. 2024Neuro-symbolic Learning Yielding Logical Constraintscited by 12
  11. 2021Thinking Fast and Slow in AI: the Role of Metacognitioncited by 11
  12. 2024The Instinctive Bias: Spurious Images lead to Illusion in MLLMscited by 11
38 more
  1. 2024TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detectioncited by 10
  2. 2023Knowledge Engineering using Large Language Modelscited by 9
  3. 2023Symbolic Regression via Control Variable Genetic Programmingcited by 8
  4. 2021Making Human-Like Trade-offs in Constrained Environments by Learning from Demonstrationscited by 7
  5. 2024Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecturecited by 7
  6. 2022Combining Fast and Slow Thinking for Human-like and Efficient Navigation in Constrained Environmentscited by 5
  7. 2022When Is It Acceptable to Break the Rules? Knowledge Representation of Moral Judgement Based on Empirical Datacited by 5
  8. 2023Describing and Organizing Semantic Web and Machine Learning Systems in the SWeMLS-KGcited by 5
  9. 2022The Roles and Modes of Human Interactions with Automated Machine Learning Systemscited by 4
  10. 2022Sampling Through the Lens of Sequential Decision Makingcited by 4
  11. 2024Pixels and Predictions: Potential of GPT-4V in Meteorological Imagery Analysis and Forecast Communicationcited by 4
  12. 2024Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principlescited by 4
  13. 2025MADRA: Multi-Agent Debate for Risk-Aware Embodied Planningcited by 4
  14. 2022Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformerscited by 3
  15. 2023Knowledge-enhanced Neural Machine Reasoning: A Reviewcited by 3
  16. 2023Fast and Slow Planningcited by 3
  17. 2024Synergising Human-like Responses and Machine Intelligence for Planning in Disaster Responsecited by 3
  18. 2024Intersymbolic AI: Interlinking Symbolic AI and Subsymbolic AIcited by 3
  19. 2025EZ-Sort: Efficient Pairwise Comparison via Zero-Shot CLIP-Based Pre-Ordering and Human-in-the-Loop Sortingcited by 3
  20. 2025Think Before You Move: Latent Motion Reasoning for Text-to-Motion Generationcited by 3
  21. 2026DarwinNet: An Evolutionary Network Architecture for Agent-Driven Protocol Synthesiscited by 3
  22. 2021HySTER: A Hybrid Spatio-Temporal Event Reasonercited by 2
  23. 2023NEOLAF, an LLM-powered neural-symbolic cognitive architecturecited by 2
  24. 2023From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoningcited by 2
  25. 2023Trust, Accountability, and Autonomy in Knowledge Graph-based AI for Self-determinationcited by 2
  26. 2024Toward A Causal Framework for Modeling Perceptioncited by 2
  27. 2025System 0/1/2/3: Quad-process theory for multi-timescale embodied collective cognitive systemscited by 2
  28. 2025Large Language Model Meets Constraint Propagationcited by 2
  29. 2025KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generationcited by 2
  30. 2025Neuro-Symbolic Frameworks: Conceptual Characterization and Empirical Comparative Analysiscited by 2
  31. 2021Comprehensive Multi-Agent Epistemic Planningcited by 1
  32. 2022Modeling Human Behavior Part II -- Cognitive approaches and Uncertaintycited by 1
  33. 2023Value-based Fast and Slow AI Nudgingcited by 1
  34. 2023Integrating Symbolic Reasoning into Neural Generative Models for Design Generationcited by 1
  35. 2023Vertical Symbolic Regressioncited by 1
  36. 2024A Neurosymbolic Fast and Slow Architecture for Graph Coloringcited by 1
  37. 2025Reflections on "Can AI Understand Our Universe?"cited by 1
  38. 2025Continuum-Interaction-Driven Intelligence: Human-Aligned Neural Architecture via Crystallized Reasoning and Fluid Generationcited by 1

50 most cited of 67 All 67 (JSON)