Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.09985 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918494001430528 |
|---|---|
| author | Cano, Leonardo Hernandez Zareski, Ivan Amouri, Luisa El Zhao, Pinzhe Mascini, Max Sansone, Emanuele Pu, Yewen Zhao, Bonan Kryven, Marta |
| author_facet | Cano, Leonardo Hernandez Zareski, Ivan Amouri, Luisa El Zhao, Pinzhe Mascini, Max Sansone, Emanuele Pu, Yewen Zhao, Bonan Kryven, Marta |
| contents | A core challenge in program synthesis is online library learning: the incremental acquisition of reusable abstractions under uncertainty about future task demands. Existing algorithms treat library learning as retrospective compression over a static task distribution, where the learned library is determined by the corpus of past tasks. However, real-world learning domains are often non-stationary, with tasks arising from a generative process that evolves over time. We propose and test the hypothesis that in non-stationary domains human library learning selects abstractions prospectively: targeting compression of future tasks. We study this question using the Pattern Builder Task, a visual program synthesis paradigm in which participants construct increasingly complex geometric patterns from a small set of primitives, transformations, and custom helpers that carry forward across trials. Using this task, we conduct two experiments with complementary latent curricula, designed to dissociate between behaviors consistent with prospective compression, and alternative library learning accounts. Using six computational models spanning online library learning strategies, we show that human abstraction behavior reflects sensitivity to latent, non-stationary structure in the task-generating process. This behavior is consistent with prospective compression, and cannot be captured by existing retrospective compression-based algorithms, or inductive biases modeled by LLM-based program synthesis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_09985 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Prospective Compression in Human Abstraction Learning Cano, Leonardo Hernandez Zareski, Ivan Amouri, Luisa El Zhao, Pinzhe Mascini, Max Sansone, Emanuele Pu, Yewen Zhao, Bonan Kryven, Marta Artificial Intelligence Machine Learning Neural and Evolutionary Computing A core challenge in program synthesis is online library learning: the incremental acquisition of reusable abstractions under uncertainty about future task demands. Existing algorithms treat library learning as retrospective compression over a static task distribution, where the learned library is determined by the corpus of past tasks. However, real-world learning domains are often non-stationary, with tasks arising from a generative process that evolves over time. We propose and test the hypothesis that in non-stationary domains human library learning selects abstractions prospectively: targeting compression of future tasks. We study this question using the Pattern Builder Task, a visual program synthesis paradigm in which participants construct increasingly complex geometric patterns from a small set of primitives, transformations, and custom helpers that carry forward across trials. Using this task, we conduct two experiments with complementary latent curricula, designed to dissociate between behaviors consistent with prospective compression, and alternative library learning accounts. Using six computational models spanning online library learning strategies, we show that human abstraction behavior reflects sensitivity to latent, non-stationary structure in the task-generating process. This behavior is consistent with prospective compression, and cannot be captured by existing retrospective compression-based algorithms, or inductive biases modeled by LLM-based program synthesis. |
| title | Prospective Compression in Human Abstraction Learning |
| topic | Artificial Intelligence Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2605.09985 |