FunctionEvolve: Structure-Guided Symbolic Regression with LLMs

2026-06-05

AI Summary

This work addresses the limitation of existing large language model (LLM)-driven symbolic regression methods, which lack explicit modeling of mathematical expression structure and consequently struggle to reliably recover exact formulas. To overcome this, the authors propose FunctionEvolve, a novel framework that introduces explicit structural guidance into LLM-based symbolic regression for the first time. FunctionEvolve organizes evolutionary search using expression trees and integrates structural summarization, local tree editing, and structure-aware coefficient optimization to enable efficient, structure-transparent exploration. Evaluated on 129 synthetic benchmarks from LLM-SRBench, FunctionEvolve achieves 82.9% SA@50 and 55.8% SA@1, outperforming current baselines by factors of 4.5 and 3.6, respectively, thereby substantially enhancing the recovery of precise symbolic expressions.

Abstract

Symbolic regression aims to uncover explicit scientific laws from data. Recent methods use LLMs to guide mutation from background text, which is more directed than random genetic programming. However, exact symbolic recovery requires both semantic guidance and explicit structure, so that domain-informed search are carried out through valid symbolic representation. Current LLM-driven systems remain structure-blind: they select among opaque candidates, lack explicit mechanisms for local mutation, and rely on brittle coefficient fitting that can undervalue correct skeletons. We propose FunctionEvolve, an evolutionary framework using expression trees to organize the whole search: structural summaries promote diverse parent selection, local tree edits preserve useful subexpressions, and structure-aware fitting decomposes, constrains, and simplifies coefficients for more reliable scoring. It uses only elementary function families, without additional domain-specific rules limiting generalization. On the 129-task synthetic subset of LLM-SRBench, FunctionEvolve with \emph{Claude Opus 4.6} recovers 107 exact forms, reaching 82.9% SA@50, 4.5x above same-backbone baselines, and 55.8% SA@1, 3.6x above the strongest previously published top-1 result. Ablations show that structure-visible search is central to reliable recovery, with LLM-guided refinements and structure-aware coefficient optimization serving as essential proposal and scoring mechanisms. We also audit the benchmark and show that collinearity in its materials-science subset creates identifiability issues.

Problem

• symbolic regression
• structure-aware search
• expression trees
• coefficient fitting
• function recovery

Innovation

• symbolic regression
• expression trees
• structure-aware optimization
• LLM-guided evolution
• coefficient fitting