Iterated Agent for Symbolic Regression

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Song, Zhuo-Yang, Cai, Zeyu, Zhang, Shutao, Wei, Jiashen, Pan, Jichen, Qiu, Shi, Cao, Qing-Hong, Hou, Tie-Jiun, Liu, Xiaohui, Luo, Ming-xing, Zhu, Hua Xing
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915542306127872
author Song, Zhuo-Yang
Cai, Zeyu
Zhang, Shutao
Wei, Jiashen
Pan, Jichen
Qiu, Shi
Cao, Qing-Hong
Hou, Tie-Jiun
Liu, Xiaohui
Luo, Ming-xing
Zhu, Hua Xing
author_facet Song, Zhuo-Yang
Cai, Zeyu
Zhang, Shutao
Wei, Jiashen
Pan, Jichen
Qiu, Shi
Cao, Qing-Hong
Hou, Tie-Jiun
Liu, Xiaohui
Luo, Ming-xing
Zhu, Hua Xing
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08317
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Iterated Agent for Symbolic Regression
Song, Zhuo-Yang
Cai, Zeyu
Zhang, Shutao
Wei, Jiashen
Pan, Jichen
Qiu, Shi
Cao, Qing-Hong
Hou, Tie-Jiun
Liu, Xiaohui
Luo, Ming-xing
Zhu, Hua Xing
Computational Physics
Instrumentation and Methods for Astrophysics
Artificial Intelligence
Machine Learning
High Energy Physics - Phenomenology
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/.
title Iterated Agent for Symbolic Regression
topic Computational Physics
Instrumentation and Methods for Astrophysics
Artificial Intelligence
Machine Learning
High Energy Physics - Phenomenology
url https://arxiv.org/abs/2510.08317