Metraipolis › archive › dc_58da2ff339c9
Hypothesis-guided discovery of cognitive algorithms via program refinement — arXiv:2610.02523
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02523
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T22:49:01.556Z
- SHA-256 of the archived text
b4adf512f0cff0aac240ba04b83537ba31d9a1bdaa5d4260999348704792ba07- Stable URL of this page
https://metraipolis.com/documento/dc_58da2ff339c9
How to cite
Hypothesis-guided discovery of cognitive algorithms via program refinement — arXiv:2610.02523 — arXiv, https://arxiv.org/abs/2610.02523 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_58da2ff339c9 (Metraipolis archive dc_58da2ff339c9, sha256 b4adf512f0cff0aac240ba04b83537ba31d9a1bdaa5d4260999348704792ba07)
BibTeX
@misc{dc58da2ff339c9,
title = {Hypothesis-guided discovery of cognitive algorithms via program refinement — arXiv:2610.02523},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02523},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_58da2ff339c9; sha256 b4adf512f0cff0aac240ba04b83537ba31d9a1bdaa5d4260999348704792ba07},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02523. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Developing cognitive models of algorithmic reasoning from behavioral data is a central problem in cognitive science that challenges current methods. Traditional approaches to cognitive modeling are interpretable and benefit from human expertise, but lack flexibility and scalability. Emerging techniques using large language models (LLMs) for de novo generation of cognitive models are scalable and flexible, but lack a role for human expertise and have mostly been applied to simpler tasks than algorithm recovery. We propose a hybrid system that treats discovery of cognitive algorithms as a program refinement problem. Human-created cognitive models are expressed as probabilistic programs and provided to a system of LLM agents with a mandate to: identify mismatches between model and behavior; propose code-level modifications within researcher-specified constraints; and verify structural fidelity. Revisions propagate to a probabilistic inference module that performs inference for latent variables and data likelihood computations. We evaluate the pipeline on human behavior in a problem-solving paradigm that exposes a variety of cognitive algorithms. Revised models consistently improve model fit relative to ancestral models and reveal a small set of recurring innovations that capture meaningful behavioral variability in this task. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.02523 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-05T22:45:55.594Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).