发表机构
Northwestern Polytechnical University; National University of Singapore; University of Toronto; Chinese Academy of Sciences; Huazhong University of Science and Technology; The University of Tokyo（西北工业大学; 新加坡国立大学; 多伦多大学; 中国科学院; 华中科技大学; 东京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对计算材料发现中多算法工具重复应用的挑战，提出MAESTRO LLM智能体系统，可完成MOF全筛选流程，发现传统方法易忽略的高性能材料。
AI 中文摘要
多尺度任务的协调是计算材料发现的有效策略，但反复应用各类算法和工具使其面临挑战。我们提出MAESTRO，一种大语言模型（LLM）智能体系统，可执行金属有机框架（MOF）的完整筛选流程。它处理大量MOF文献，将相关出版物与其晶体结构关联，整理结果形成可计算数据库，再通过计算成本逐步提升的策略进行筛选。在湿烟道气分离场景中识别出的有前景候选材料均来自无关研究。通过连接计算材料发现的异构阶段，MAESTRO的基于LLM的智能体可跨应用领域运行，发现传统筛选方法可能不会考虑的高性能材料。
英文摘要
The coordination of multi-scale tasks is an effective strategy for computational materials discovery, yet the repeated application of diverse algorithms and tools renders it challenging. We report MAESTRO, a large language model (LLM) agent system capable of executing the entire screening pipeline for metal-organic frameworks (MOFs). It processes a large body of MOF literature, links relevant publications to their crystal structures, and curates the results into a computation-ready database, which is then screened through a strategy of progressively increasing computational cost. The promising candidates identified for separation under wet flue gas conditions all originate from unrelated studies. By connecting the heterogeneous stages of computational materials discovery, the LLM-based agents of MAESTRO can operate across application domains and uncover high-performance materials that conventional screening approaches would be unlikely to consider.
