From LLM to Agent: A large-language-model-driven machine learning framework for catalyst design of MgH2 dehydrogenation

作者：Tongao Yao, Yang Yang, Jianghao Cai, Rui Liu, Zhaoyan Dong, Xiaotian Tang, Xuqiang Shao, Zhijun Gao, Guangyao An, Weijie Yang · 发表于：Journal of Magnesium and Alloys · 年份：2025 · DOI：10.1016/j.jma.2025.08.021 · 被引用次数：15 · 研究领域：Hydrogen Storage and Materials、Hybrid Renewable Energy Systems、Superconductivity in MgB2 and Alloys

• AI framework automates MgH 2 catalyst data extraction from literature. • LLM to Agent approach accelerates MgH 2 catalyst discovery and design. • Machine learning predicts MgH 2 dehydrogenation with high accuracy. • Cat-Advisor provides actionable catalyst design recommendations. • Open database and AI tools advance hydrogen storage materials research. Magnesium hydride (MgH 2 ), a promising high-capacity hydrogen storage material, is hindered by slow dehydrogenation kinetics. AI-driven catalyst discovery to address this is often hampered by the laborious extraction of data from unstructured literature. To overcome this, we introduce a transformative “LLM to Agent” framework that synergistically integrates Large Language Models (LLMs) for automated data curation with Machine Learning (ML) for predictive design. We automatically constructed a comprehensive database of 809 MgH 2 catalysts (6555 data rows) with high fidelity and an ∼40-fold acceleration over manual methods. The resulting ML models achieved high accuracy (average R² > 0.91) in predicting dehydrogenation temperature and activation energy, subsequently guiding a Genetic Algorithm (GA) in an exploratory inverse design that autonomously uncovered key design principles for high-performance catalysts. Encouragingly, a strong alignment was found between these AI-discovered principles and the design strategies of recently reported, state-of-the-art experimental systems, providing substantial evidence for the validity o...