# People construct simplified mental representations to plan

arXiv: https://arxiv.org/abs/2105.06948 · HTML: https://mlsanity.com/paper/2105.06948/

## 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 (most cited first, 1 of 1)

- [Towards a Quantum-Like Cognitive Architecture for Decision-Making](https://mlsanity.com/paper/1905.05176/) (2019)

## Built on by (most cited first, 30 of 47)

- [Building Machines that Learn and Think with People](https://mlsanity.com/paper/2408.03943/) (2024)
- [From task structures to world models: What do LLMs know?](https://mlsanity.com/paper/2310.04276/) (2023)
- [Learning adaptive planning representations with natural language guidance](https://mlsanity.com/paper/2312.08566/) (2023)
- [Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learning](https://mlsanity.com/paper/2309.07742/) (2023)
- [Humans decompose tasks by trading off utility and computational cost](https://mlsanity.com/paper/2211.03890/) (2022)
- [Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models](https://mlsanity.com/paper/2507.12547/) (2025)
- [ANPL: Towards Natural Programming with Interactive Decomposition](https://mlsanity.com/paper/2305.18498/) (2023)
- [Preference-Conditioned Language-Guided Abstraction](https://mlsanity.com/paper/2402.03081/) (2024)
- [Imagining and building wise machines: The centrality of AI metacognition](https://mlsanity.com/paper/2411.02478/) (2024)
- [Learning with Language-Guided State Abstractions](https://mlsanity.com/paper/2402.18759/) (2024)
- [AI for Mathematics: A Cognitive Science Perspective](https://mlsanity.com/paper/2310.13021/) (2023)
- [Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input](https://mlsanity.com/paper/2405.14769/) (2024)
- [On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning](https://mlsanity.com/paper/2210.16877/) (2022)
- [DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multi-Modal Reinforcement Learning](https://mlsanity.com/paper/2409.19709/) (2024)
- [What Images are More Memorable to Machines?](https://mlsanity.com/paper/2211.07625/) (2022)
- [Concept Alignment as a Prerequisite for Value Alignment](https://mlsanity.com/paper/2310.20059/) (2023)
- [Bayesian Reinforcement Learning with Limited Cognitive Load](https://mlsanity.com/paper/2305.03263/) (2023)
- [Satisficing Exploration for Deep Reinforcement Learning](https://mlsanity.com/paper/2407.12185/) (2024)
- [People use fast, goal-directed simulation to reason about novel games](https://mlsanity.com/paper/2407.14095/) (2024)
- [Evaluating Language Models' Evaluations of Games](https://mlsanity.com/paper/2510.10930/) (2025)
- [Incentives 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 Model](https://mlsanity.com/paper/2411.17724/) (2024)
- [Sample-Efficient Behavior Cloning Using General Domain Knowledge](https://mlsanity.com/paper/2501.16546/) (2025)
- [Cognitive maps are generative programs](https://mlsanity.com/paper/2504.20628/) (2025)
- [How attention simplifies mental representations for planning](https://mlsanity.com/paper/2506.09520/) (2025)
- [Memory Allocation in Resource-Constrained Reinforcement Learning](https://mlsanity.com/paper/2506.17263/) (2025)
- [Estimating cognitive biases with attention-aware inverse planning](https://mlsanity.com/paper/2510.25951/) (2025)
- [Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents](https://mlsanity.com/paper/2602.22523/) (2026)
- [Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling](https://mlsanity.com/paper/2607.04409/) (2026)
- [A space of goals: the cognitive geometry of informationally bounded agents](https://mlsanity.com/paper/2111.03699/) (2021)
- [Metareasoning constraints couple narratives, affect and cognition](https://mlsanity.com/paper/2502.09487/) (2025)

## 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.