Abstract
Understanding data with complex patterns is a significant part of the journey toward accurate data prediction and interpretation. The relationships between input and output variables can unlock diverse advancement opportunities across various processes. However, most AI models attempting to uncover these patterns are not explainable or remain opaque, offering little interpretation. This paper explores an approach in explainable AI by introducing a multi-agent system (MaSR) for extracting equations between features using data. We developed a novel approach to perform symbolic regression by discovering mathematical functions using a multi-agent system of LLMs. This system addresses the traditional challenges of genetic optimization, such as random seed generation, complexity, and the explainability of the final equation. We utilize the in-context learning capabilities of LLMs trained on vast amounts of data to generate accurate equations more quickly. This study presents research on expanding the reasoning capacities of large language models alongside their mathematical understanding. The paper serves as a benchmark in understanding the capabilities of LLMs in mathematical reasoning and can be a starting point for solving numerous complex tasks using LLMs. The MaSR framework can be applied in various areas where the reasoning capabilities of LLMs are tested for complex and sequential tasks. MaSR can explain the predictions of black-box models, develop data-driven models, identify complex relationships within the data, assist in feature engineering and feature selection, and generate synthetic data equations to address data scarcity, which are explored as further directions for future research in this paper.