mlsanityData to 14 Oct 2026

People construct simplified mental representations to plan

arXiv 2105.06948 ↗First posted 14 May 2021cs.AIcited by 47

Not on the map. Why?

Abstract (arXiv)

One of the most striking features of human cognition is the capacity to plan. Two aspects of human planning stand out: its efficiency and flexibility. Efficiency is especially impressive because plans must often be made in complex environments, and yet people successfully plan solutions to myriad everyday problems despite having limited cognitive resources. Standard accounts in psychology, economics, and artificial intelligence have suggested human planning succeeds because people have a complete representation of a task and then use heuristics to plan future actions in that representation. However, this approach generally assumes that task representations are fixed. Here, we propose that task representations can be controlled and that such control provides opportunities to quickly simplify problems and more easily reason about them. We propose a computational account of this simplification process and, in a series of pre-registered behavioral experiments, show that it is subject to online cognitive control and that people optimally balance the complexity of a task representation and its utility for planning and acting. These results demonstrate how strategically perceiving and conceiving problems facilitates the effective use of limited cognitive resources.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). Builds on 1 of its 59 references that are in the map. First posted on arXiv 14 May 2021.

Builds on

1 of 59 references.

References · 1

  1. 2019Towards a Quantum-Like Cognitive Architecture for Decision-Makingcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 7; 2024: 11; 2025: 13; 2026: 11.

47 papers.

Sort:

By area:

  1. 2024Building Machines that Learn and Think with Peoplecited by 73
  2. 2023From task structures to world models: What do LLMs know?cited by 46
  3. 2023Learning adaptive planning representations with natural language guidancecited by 36
  4. 2023Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learningcited by 22
  5. 2022Humans decompose tasks by trading off utility and computational costcited by 18
  6. 2025Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Modelscited by 14
  7. 2023ANPL: Towards Natural Programming with Interactive Decompositioncited by 13
  8. 2024Preference-Conditioned Language-Guided Abstractioncited by 12
  9. 2024Imagining and building wise machines: The centrality of AI metacognitioncited by 12
  10. 2024Learning with Language-Guided State Abstractionscited by 11
  11. 2023AI for Mathematics: A Cognitive Science Perspectivecited by 10
  12. 2024Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Inputcited by 8
35 more
  1. 2022On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learningcited by 6
  2. 2024DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multi-Modal Reinforcement Learningcited by 6
  3. 2022What Images are More Memorable to Machines?cited by 5
  4. 2023Concept Alignment as a Prerequisite for Value Alignmentcited by 5
  5. 2023Bayesian Reinforcement Learning with Limited Cognitive Loadcited by 4
  6. 2024Satisficing Exploration for Deep Reinforcement Learningcited by 4
  7. 2024People use fast, goal-directed simulation to reason about novel gamescited by 4
  8. 2025Evaluating Language Models' Evaluations of Gamescited by 4
  9. 2024Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Modelcited by 2
  10. 2025Sample-Efficient Behavior Cloning Using General Domain Knowledgecited by 2
  11. 2025Cognitive maps are generative programscited by 2
  12. 2025How attention simplifies mental representations for planningcited by 2
  13. 2025Memory Allocation in Resource-Constrained Reinforcement Learningcited by 2
  14. 2025Estimating cognitive biases with attention-aware inverse planningcited by 2
  15. 2026Cognitive Models and AI Algorithms Provide Templates for Designing Language Agentscited by 2
  16. 2026Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modelingcited by 2
  17. 2021A space of goals: the cognitive geometry of informationally bounded agentscited by 1
  18. 2025Metareasoning constraints couple narratives, affect and cognitioncited by 1
  19. 2025Multi-Robot Collaboration through Reinforcement Learning and Abstract Simulationcited by 1
  20. 2025Analogy making as amortised model constructioncited by 1
  21. 2025Multi-layer Abstraction for Nested Generation of Options (MANGO) in Hierarchical Reinforcement Learningcited by 1
  22. 2025The Alignment Bottleneckcited by 1
  23. 2026How Clinicians Think and What AI Can Learn From Itcited by 1
  24. 2026Growing a Neural Network in Breadth, Depth, and Timecited by 1
  25. 2026What Is Worth Representing? Representational Empowerment for Continual Model Constructioncited by 1
  26. 2022To think inside the box, or to think out of the box? Scientific discovery via the reciprocation of insights and conceptscited by 0
  27. 2024Principles of frugal inference and controlcited by 0
  28. 2024Learning telic-controllable state representationscited by 0
  29. 2025Information-Seeking Decision Strategies Mitigate Risk in Dynamic, Uncertain Environmentscited by 0
  30. 2026PaperGuide: Making Small Language-Model Paper-Reading Agents More Efficientcited by 0
  31. 2026The Dual Role of Abstracting over the Irrelevant in Symbolic Explanations: Cognitive Effort vs. Understandingcited by 0
  32. 2026Abstract Sim2Real through Approximate Information Statescited by 0
  33. 2026Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundationscited by 0
  34. 2026Orbis 2: A Hierarchical World Model for Drivingcited by 0
  35. 2026The syntax and semantics of goalscited by 0