# Learning abstract structure for drawing by efficient motor program induction

arXiv: https://arxiv.org/abs/2008.03519 · HTML: https://mlsanity.com/paper/2008.03519/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2020.

## Built on by (most cited first, 23 of 23)

- [Language to Rewards for Robotic Skill Synthesis](https://mlsanity.com/paper/2306.08647/) (2023)
- [Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement](https://mlsanity.com/paper/2310.08559/) (2023)
- [Leveraging Language to Learn Program Abstractions and Search Heuristics](https://mlsanity.com/paper/2106.11053/) (2021)
- [Communicating Natural Programs to Humans and Machines](https://mlsanity.com/paper/2106.07824/) (2021)
- [PoE-World: Compositional World Modeling with Products of Programmatic Experts](https://mlsanity.com/paper/2505.10819/) (2025)
- [Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning](https://mlsanity.com/paper/2402.06025/) (2024)
- [Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language](https://mlsanity.com/paper/2306.02797/) (2023)
- [Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines](https://mlsanity.com/paper/2205.11558/) (2022)
- [ANPL: Towards Natural Programming with Interactive Decomposition](https://mlsanity.com/paper/2305.18498/) (2023)
- [Learning with Language-Guided State Abstractions](https://mlsanity.com/paper/2402.18759/) (2024)
- [Map Induction: Compositional spatial submap learning for efficient exploration in novel environments](https://mlsanity.com/paper/2110.12301/) (2021)
- [Programmatic Reward Design by Example](https://mlsanity.com/paper/2112.08438/) (2021)
- [A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines](https://mlsanity.com/paper/2204.09772/) (2022)
- [Identifying concept libraries from language about object structure](https://mlsanity.com/paper/2205.05666/) (2022)
- [Compositional diversity in visual concept learning](https://mlsanity.com/paper/2305.19374/) (2023)
- [Action abstractions for amortized sampling](https://mlsanity.com/paper/2410.15184/) (2024)
- [Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents](https://mlsanity.com/paper/2505.14104/) (2025)
- [Cognitive maps are generative programs](https://mlsanity.com/paper/2504.20628/) (2025)
- [Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance](https://mlsanity.com/paper/2503.15886/) (2025)
- [Online library learning in human visual puzzle solving](https://mlsanity.com/paper/2603.23244/) (2026)
- [Path-dependent program induction under resource constraints explains human sequence learning](https://mlsanity.com/paper/2606.20623/) (2026)
- [Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition](https://mlsanity.com/paper/2603.07911/) (2026)
- [Prospective Compression in Human Abstraction Learning](https://mlsanity.com/paper/2605.09985/) (2026)

## Abstract (arXiv)

Humans flexibly solve new problems that differ qualitatively from those they were trained on. This ability to generalize is supported by learned concepts that capture structure common across different problems. Here we develop a naturalistic drawing task to study how humans rapidly acquire structured prior knowledge. The task requires drawing visual objects that share underlying structure, based on a set of composable geometric rules. We show that people spontaneously learn abstract drawing procedures that support generalization, and propose a model of how learners can discover these reusable drawing programs. Trained in the same setting as humans, and constrained to produce efficient motor actions, this model discovers new drawing routines that transfer to test objects and resemble learned features of human sequences. These results suggest that two principles guiding motor program induction in the model - abstraction (general programs that ignore object-specific details) and compositionality (recombining previously learned programs) - are key for explaining how humans learn structured internal representations that guide flexible reasoning and learning.