Apr 22, 2026 · cond-mat.mtrl-sciJ/K move · Enter open · S save
Ryo Tamura, Haruhiko Morito, Yuna Oikawa, Guillaume Deffrennes+6
Center for Basic Research on Materials, National Institute for Materials Science, 1-1 Namiki, Tsukuba, Ibaraki 305-0044, Japan · Graduate School of Frontier Sciences, The University of Tokyo, 5-1-5 Kashiwa-no-ha, Kashiwa, Chiba 277-8561, Japan · RIKEN Center for Advanced Intelligence Project, 1-4-1 Nihonbashi, Chuo-ku, Tokyo 103-0027, Japan · Core Facility Center, Tohoku University, 2-1-1 Katahira, Aoba-ku, Sendai 980-8577, Japan · Univ. Grenoble Alpes, CNRS, Grenoble INP, SIMaP, F-38000 Grenoble, France
Constructing phase diagrams for multicomponent alloys requires extensive experimental measurements and is a time-consuming task. Here we investigate whether large language models (LLMs) can guide experimental planning for phase diagram construction. In our framework, a general-purpose LLM serves as the experimental planner, suggesting compositions for measurement at each cycle in a closed loop with high-throughput synthesis and X-ray diffraction phase identification. Using this framework, we experimentally constructed the ternary phase diagram of the Co-Al-Ge system at 900 degree C through iterative synthesis and characterization. We compared two strategies that differ in how the initial compositions are selected: one uses predictions from a domain-specific LLM trained on phase diagram data (aLLoyM), while the other relies solely on the general-purpose LLM. The two strategies exhibited complementary strengths. aLLoyM directed the initial measurements toward compositionally complex regions in the interior of the ternary diagram, enabling the earliest discovery of all three novel phases that form only in the ternary system. In contrast, the general-purpose LLM adopted a textbook-like approach which efficiently identified a larger number of phases in fewer cycles. In addition, a simulated benchmark comparing the LLM against conventional machine learning confirmed that the LLM achieves more efficient exploration. The results demonstrate that LLMs have high potential as experimental planners for phase diagram construction.