arXiv 2603.157122026-03-16cond-mat.mtrl-scics.AI

通过检索增强生成发现高效熵催化剂

LLM-Driven Discovery of High-Entropy Catalysts via Retrieval-Augmented Generation

School of Biomedical Sciences, Li Ka Shing Faculty of Medicine, The University of Hong Kong（香港大学生物医学科学学院，利卡申医学学院）

AI Scientists, Xinyi Lin, Danqing Yin, Ying Guo

发表信息：: Open Conference of AI Agents for Science 2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文展示如何利用大语言模型加速催化剂发现，通过检索增强生成框架生成250多个候选催化剂，其中82%具有热力学稳定性，同时满足多目标约束，最佳催化剂在性能和成本上均有显著提升。

摘要：

CO2还原需要高效的催化剂，但材料发现仍受制于10-20年的开发周期，需要深厚的领域专业知识。本文展示了如何通过检索增强生成框架，使GPT-4能够通过访问包含50000多个已知材料的数据库，在高通量材料设计中应用通用语言理解。我们的方法生成了超过250个催化剂候选者，其中82%具有热力学稳定性，同时满足多目标约束：68%实现了< $100/kg的成本，具有金属导电性（带隙<0.1eV）和机械稳定性（B/G>1.75）。最佳性能的Fe0.2Co0.2Ni0.2Ir0.1Ru0.3达到0.285V限制电位（比IrO2提高25%），而Cr0.2Fe0.2Co0.3Ni0.2Mo0.1在性能-成本平衡方面达到$18/kg。火山图分析证实，78%的LLM生成的催化剂集中在理论活性最优附近，而我们的系统相比传统高通量筛选具有200倍的计算效率。通过展示检索增强生成能够在物理约束下引导AI创造力而不牺牲探索，本工作演示了一种方法，其中自然语言接口可以流利材料发现流程，使研究人员更高效地探索化学空间，同时LLM在结果解释和假设生成中提供帮助。

英文摘要：

CO2 reduction requires efficient catalysts, yet materials discovery remains bottlenecked by 10-20 year development cycles requiring deep domain expertise. This paper demonstrates how large language models can assist the catalyst discovery process by helping researchers explore chemical spaces and interpret results when augmented with retrieval-based grounding. We introduce a retrieval-augmented generation framework that enables GPT-4 to navigate chemical space by accessing a database of 50,000+ known materials, adapting general-purpose language understanding for high-throughput materials design. Our approach generated over 250 catalyst candidates with an 82% thermodynamic stability rate while addressing multi-objective constraints: 68% achieved <$100/kg cost with metallic conductivity (band gap<0.1eV) and mechanical stability (B/G>1.75). The best-performing Fe0.2Co0.2Ni0.2Ir0.1Ru0.3 achieves 0.285V limiting potential (25% improvement over IrO2), while Cr0.2Fe0.2Co0.3Ni0.2Mo0.1 optimally balances performance-cost trade-offs at $18/kg. Volcano plot analysis confirms that 78% of LLM-generated catalysts cluster near the theoretical activity optimum, while our system achieves 200x computational efficiency compared to traditional high-throughput screening. By demonstrating that retrieval-augmented generation can ground AI creativity in physical constraints without sacrificing exploration, this work demonstrates an approach where natural language interfaces can streamline materials discovery workflows, enabling researchers to explore chemical spaces more efficiently while the LLM assists in result interpretation and hypothesis generation.

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。