# Hypothesis-guided discovery of cognitive algorithms via program refinement

arXiv: https://arxiv.org/abs/2610.02523 · HTML: https://mlsanity.com/paper/2610.02523/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 42 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 15 of 15)

- [DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning](https://mlsanity.com/paper/2006.08381/) (2020)
- [An Introduction to Probabilistic Programming](https://mlsanity.com/paper/1809.10756/) (2018)
- [Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning](https://mlsanity.com/paper/1907.09620/) (2019)
- [Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI](https://mlsanity.com/paper/2507.14172/) (2025)
- [Cognitive Model Priors for Predicting Human Decisions](https://mlsanity.com/paper/1905.09397/) (2019)
- [Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning](https://mlsanity.com/paper/2402.06025/) (2024)
- [One Model for the Learning of Language](https://mlsanity.com/paper/1711.06301/) (2017)
- [Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language](https://mlsanity.com/paper/2306.02797/) (2023)
- [Generating Computational Cognitive Models using Large Language Models](https://mlsanity.com/paper/2502.00879/) (2025)
- [LLM-Guided Probabilistic Program Induction for POMDP Model Estimation](https://mlsanity.com/paper/2505.02216/) (2025)
- [Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist](https://mlsanity.com/paper/2606.26448/) (2026)
- [Modeling Others' Minds as Code](https://mlsanity.com/paper/2510.01272/) (2025)
- [Finding structure in logographic writing with library learning](https://mlsanity.com/paper/2405.06906/) (2024)
- [auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation](https://mlsanity.com/paper/2606.26460/) (2026)
- [Discovering Differences in Strategic Behavior Between Humans and LLMs](https://mlsanity.com/paper/2602.10324/) (2026)

## Abstract (arXiv)

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.