# Exploring the hierarchical structure of human plans via program generation

arXiv: https://arxiv.org/abs/2311.18644 · HTML: https://mlsanity.com/paper/2311.18644/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 74 references that are in the map.
- First posted on arXiv 30 Nov 2023.

## Builds on (most cited first, 6 of 6)

- [Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review](https://mlsanity.com/paper/1805.00909/) (2018)
- [People infer recursive visual concepts from just a few examples](https://mlsanity.com/paper/1904.08034/) (2019)
- [Humans decompose tasks by trading off utility and computational cost](https://mlsanity.com/paper/2211.03890/) (2022)
- [Peano: Learning Formal Mathematical Reasoning](https://mlsanity.com/paper/2211.15864/) (2022)
- [Representational efficiency outweighs action efficiency in human program induction](https://mlsanity.com/paper/1807.07134/) (2018)
- [Habits of Mind: Reusing Action Sequences for Efficient Planning](https://mlsanity.com/paper/2306.05298/) (2023)

## Built on by (most cited first, 12 of 12)

- [Synthesizing world models for bilevel planning](https://mlsanity.com/paper/2503.20124/) (2025)
- [Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective](https://mlsanity.com/paper/2603.14248/) (2026)
- [Harmonizing Program Induction with Rate-Distortion Theory](https://mlsanity.com/paper/2405.05294/) (2024)
- [Cognitive maps are generative programs](https://mlsanity.com/paper/2504.20628/) (2025)
- [Agent-centric learning: from external reward maximization to internal knowledge curation](https://mlsanity.com/paper/2507.22255/) (2025)
- [Online library learning in human visual puzzle solving](https://mlsanity.com/paper/2603.23244/) (2026)
- [From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents](https://mlsanity.com/paper/2604.23194/) (2026)
- [Path-dependent program induction under resource constraints explains human sequence learning](https://mlsanity.com/paper/2606.20623/) (2026)
- [Learning telic-controllable state representations](https://mlsanity.com/paper/2406.14476/) (2024)
- [Unsupervised Hierarchical Skill Discovery](https://mlsanity.com/paper/2601.23156/) (2026)
- [A Probabilistic Framework for Hierarchical Goal Recognition](https://mlsanity.com/paper/2604.22256/) (2026)
- [Prospective Compression in Human Abstraction Learning](https://mlsanity.com/paper/2605.09985/) (2026)

## Abstract (arXiv)

Human behavior is often assumed to be hierarchically structured, made up of abstract actions that can be decomposed into concrete actions. However, behavior is typically measured as a sequence of actions, which makes it difficult to infer its hierarchical structure. In this paper, we explore how people form hierarchically structured plans, using an experimental paradigm with observable hierarchical representations: participants create programs that produce sequences of actions in a language with explicit hierarchical structure. This task lets us test two well-established principles of human behavior: utility maximization (i.e. using fewer actions) and minimum description length (MDL; i.e. having a shorter program). We find that humans are sensitive to both metrics, but that both accounts fail to predict a qualitative feature of human-created programs, namely that people prefer programs with reuse over and above the predictions of MDL. We formalize this preference for reuse by extending the MDL account into a generative model over programs, modeling hierarchy choice as the induction of a grammar over actions. Our account can explain the preference for reuse and provides better predictions of human behavior, going beyond simple accounts of compressibility to highlight a principle that guides hierarchical planning.