arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.01311cs.CL
收藏

Catalyst-Agent:基于LLM Agent的自主异质催化剂筛选

Catalyst-Agent: Autonomous heterogeneous catalyst screening with an LLM Agent

Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA(卡内基梅隆大学机械工程系,匹兹堡,PA 15213,USA);Department of Chemical and Biomolecular Engineering, University of Nebraska--Lincoln, Lincoln, NE 68588, USA(内布拉斯加大学林肯分校化学与生物分子工程系,林肯,NE 68588,USA)

Achuth Chandrasekhar, Janghoon Ock, Amir Barati Farimani

AI总结:

提出Catalyst-Agent,一种基于MCP服务器和LLM的AI代理,通过OPTIMADE API探索材料数据库、利用UMA模型计算吸附能,实现闭环自主催化剂筛选,在ORR、NRR和CO2RR反应中成功率达33-41%。

摘要:

发现针对特定应用的新型催化剂是21世纪的一项重大挑战。传统方法包括基于化学理论的耗时且昂贵的实验试错法,或基于密度泛函理论的计算密集型第一性原理方法。近期研究表明,图神经网络(GNN)等深度学习模型可以将催化剂材料的筛选速度提高多个数量级,且具有很高的准确性和保真度。在这项工作中,我们引入了Catalyst-Agent,一个基于模型上下文协议(MCP)服务器、由LLM驱动的AI代理。它可以使用OPTIMADE API探索庞大的材料数据库,进行结构修改,通过FAIRchem的AdsorbML工作流程和板坯构建使用Meta FAIRchem的UMA(GNN)模型计算吸附能,并以闭环方式向研究人员提供有用的材料建议,包括改进接近命中候选者的结构修改。我们在三个关键反应上进行了测试:氧还原反应(ORR)、氮还原反应(NRR)和CO2还原反应(CO2RR)。Catalyst-Agent在其选择和评估的所有材料中实现了33-41%的成功率,并且平均每个成功材料在1-4次试验内收敛。这项工作展示了AI代理利用其规划能力和工具使用实现自主催化剂筛选工作流程的潜力。

英文摘要:

The discovery of catalysts for electrochemical applications such as the oxygen reduction reaction (ORR), nitrogen reduction reaction (NRR), and CO2 reduction reaction (CO2RR) remains a central challenge in chemistry and materials science. Machine-learning interatomic potentials (MLIPs) and graph neural network models now accelerate individual adsorption-energy calculations by orders of magnitude relative to density functional theory. However, true large-scale screening is still blocked by human decisions: selecting candidates, constructing slabs, enumerating adsorption sites, interpreting descriptor failures, and choosing follow-up modifications. Here, we introduce Catalyst-Agent, a Model Context Protocol (MCP) server-based, LLM-powered agent that autonomously coordinates closed-loop catalyst screening. Catalyst-Agent searches materials databases through OPTIMADE, constructs slabs, computes adsorption energies using Meta FAIRchem's UMA MLIP within AdsorbML, evaluates reaction-specific descriptors, and applies structural modifications to refine near-miss candidates. In ORR, NRR, and CO2RR campaigns, Catalyst-Agent demonstrates high performance and converges in 1.40-3.41 trials per successful material on average. It identified Sn3Sc, Sn3Y, Tl3La, Pb3Y and In3Y as CO2RR candidates for further validation that were not previously reported in the literature. DFT single-point checks confirmed screening outcomes for representative NRR and CO2RR candidates. Ablations show these gains arise from chemically informed candidate selection and feedback-directed modification rather than brute-force evaluation: fully randomized screening dropped to 13.3%, 16.7%, and 0% success for ORR, NRR, and CO2RR, respectively. These results show that tool-grounded LLM agents can shift catalyst screening from manual trial-and-error toward more autonomous, reproducible and adaptive workflows.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑