arXiv：cs.AI· Huiwen Alex Yang, Mark K. Ho, Bill D. Thompson·· 5 小时前AI 评分34
通过程序精化实现假设引导的认知算法发现
Hypothesis-guided discovery of cognitive algorithms via program refinement
AI 导读
研究者提出一种混合系统，将认知算法发现视为程序精化问题：人类创建的认知模型以概率程序表达，交由一组 LLM 智能体识别模型与行为间的偏差、在研究者设定的约束内提出代码级修改并验证结构保真度，修订结果再传入概率推理模块完成隐变量推理与数据似然计算。在暴露多种认知算法的问题解决范式人类行为数据上，修订后的模型相比原始模型持续提升拟合度，并揭示出一小组反复出现的创新。
正文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.02523 [cs.AI] |
| (or arXiv:2610.02523v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02523 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Huiwen Alex Yang [view email]
[v1]
Thu, 1 Oct 2026 21:53:21 UTC (2,185 KB)
来源：arXiv：cs.AI · arxiv.org