LLM-guided phase diagram construction through high-throughput experimentation

2026-04-22

AI Summary

Constructing phase diagrams for multicomponent alloys traditionally relies on extensive, time-consuming experiments, necessitating more efficient exploration strategies. This work proposes a closed-loop active learning framework that integrates a general-purpose large language model (LLM) with a domain-specific model, aLLoyM, to iteratively recommend alloy compositions through high-throughput synthesis and X-ray diffraction characterization, enabling rapid construction of the Co–Al–Ge ternary phase diagram at 900 °C. The approach synergistically combines aLLoyM’s capability for rapid discovery of novel phases with the LLM’s superior efficiency in identifying multiphase regions. The experimental campaign successfully uncovered three new phases exclusive to the ternary system, and benchmark simulations demonstrate that the LLM significantly outperforms conventional machine learning methods in exploration efficiency.

Technology Category

• Machine Learning: Active Learning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• phase diagram construction
• multicomponent alloys
• experimental planning
• high-throughput experimentation
• large language models

Innovation

• large language models
• phase diagram construction
• high-throughput experimentation
• active learning
• materials discovery