A Multi-agent Framework for Materials Laws Discovery

Siyu Liu, Bo Hu, Beilin YE, Yun Hao, Tongqi Wen

Abstract: Uncovering the underlying laws governing correlations between different materials properties, and the structure-composition-property relationship, is essential for advancing materials theory and enabling efficient materials design. With recent advances in artificial intelligence (AI), particularly in large language models (LLMs), symbolic regression has emerged as a powerful method for deriving explicit formulas for materials laws. LLMs, with their pre-trained, cross-disciplinary knowledge, present a promising direction in "AI for Materials". In this work, we introduce a multi-agent framework based on LLMs specifically designed for symbolic regression in materials science. We demonstrate the effectiveness of the framework using the glass-forming ability (GFA) of metallic glasses as a case study, employing three characteristic temperatures as independent variables. Our framework derived an interpretable formula to describe GFA, achieving a correlation coefficient of up to 0.948 with low formula complexity. This approach outperforms standard packages such as GPlearn and demonstrates a ~30% improvement over random generation methods, owing to integrated memory and reflection mechanisms. The proposed framework can be extended to discover laws in various materials applications, supporting new materials design and enhancing the interpretation of experimental and simulation data.