摘要
构建多组分合金相图需大量实验且耗时。本文研究大语言模型（LLM）能否指导相图构建的实验规划。框架中，通用 LLM 充当实验规划器，在与高通量合成及 X 射线衍射表征的闭环中，迭代建议待测成分。实验成功构建了 Co-Al-Ge 三元系相图。对比显示：领域专用 LLM 擅长定位复杂区域以发现新相，而通用 LLM 能以更少周期高效识别更多相。结果表明 LLM 作为实验规划器具有巨大潜力。
AI 推荐理由
论文核心研究 LLM 作为实验规划器，在闭环中生成多步测量计划以构建相图。
研究机构
1 Center for Basic Research on Materials, National Institute for Materials Science, 1-1 Namiki, Tsukuba, Ibaraki 305-0044, Japan
2 Graduate School of Frontier Sciences, The University of Tokyo, 1-1-5 Kashiwa-no-ha, Kashiwa, Chiba 277-8561, Japan
3 RIKEN Center for Advanced Intelligence Project, 1-4-1 Nihonbashi, Chuo-ku, Tokyo 103-0027, Japan
4 Core Facility Center, Tohoku University, 2-1-1 Katahira, Aoba-ku, Sendai 980-8577, Japan
5 Univ. Grenoble Alpes, CNRS, Grenoble INP, SIMaP, F-38000 Grenoble, France
6 Center for Green Research on Energy and Environmental Materials, National Institute for Material Science, 1-1 Namiki, Tsukuba, Ibaraki 305-0044, Japan
7 Graduate School of Science and Technology, Nara Institute of Science and Technology, Ikoma, Nara 630-0192, Japan
8 Data Science Center, Nara Institute of Science and Technology, Ikoma, Nara 630-0192, Japan
9 Research Center for Structural Materials, National Institute for Materials Science, 1-2-1 Sengen, Tsukuba, Ibaraki 305-0047, Japan
10 Graduate School of Medical Life Science, Yokohama City University, 1-7-29, Suehiro-cho, Tsurumi-ku, Kanagawa 230-0045, Japan
论文信息