{"ID":2858223,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.08317","arxiv_id":"2510.08317","title":"Iterated Agent for Symbolic Regression","abstract":"Symbolic regression (SR), the automated discovery of mathematical expressions from data, is a cornerstone of scientific inquiry. However, it is often hindered by the combinatorial explosion of the search space and a tendency to overfit. Popular methods, rooted in genetic programming, explore this space syntactically, often yielding overly complex, uninterpretable models. This paper introduces IdeaSearchFitter, a framework that employs Large Language Models (LLMs) as semantic operators within an evolutionary search. By generating candidate expressions guided by natural-language rationales, our method biases discovery towards models that are not only accurate but also conceptually coherent and interpretable. We demonstrate IdeaSearchFitter's efficacy across diverse challenges: it achieves competitive, noise-robust performance on the Feynman Symbolic Regression Database (FSReD), outperforming several strong baselines; discovers mechanistically aligned models with good accuracy-complexity trade-offs on real-world data; and derives compact, physically-motivated parametrizations for Parton Distribution Functions in a frontier high-energy physics application. IdeaSearchFitter is a specialized module within our broader iterated agent framework, IdeaSearch, which is publicly available at https://www.ideasearch.cn/.","short_abstract":"Symbolic regression (SR), the automated discovery of mathematical expressions from data, is a cornerstone of scientific inquiry. However, it is often hindered by the combinatorial explosion of the search space and a tendency to overfit. Popular methods, rooted in genetic programming, explore this space syntactically, o...","url_abs":"https://arxiv.org/abs/2510.08317","url_pdf":"https://arxiv.org/pdf/2510.08317v1","authors":"[\"Zhuo-Yang Song\",\"Zeyu Cai\",\"Shutao Zhang\",\"Jiashen Wei\",\"Jichen Pan\",\"Shi Qiu\",\"Qing-Hong Cao\",\"Tie-Jiun Hou\",\"Xiaohui Liu\",\"Ming-xing Luo\",\"Hua Xing Zhu\"]","published":"2025-10-09T15:02:56Z","proceeding":"physics.comp-ph","tasks":"[\"physics.comp-ph\",\"astro-ph.IM\",\"cs.AI\",\"cs.LG\",\"hep-ph\"]","methods":"[\"Large Language Model\",\"Language Model\"]","project_urls":"[\"https://www.ideasearch.cn/\"]","has_code":false,"code_links":[{"ID":608527,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2858223,"paper_url":"https://arxiv.org/abs/2510.08317","paper_title":"Iterated Agent for Symbolic Regression","repo_url":"https://github.com/IdeaSearch/IdeaSearch-doc","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}