Autonomous Multi-objective Alloy Design through Simulation-guided Optimization

TL;DR

AutoMAT is an autonomous framework that combines simulation, machine learning, and experimental validation to efficiently discover high-performance alloys, significantly reducing discovery time.

Contribution

The paper introduces AutoMAT, a novel hierarchical autonomous system integrating LLMs, simulations, and AI-guided optimization for alloy design without hand-curated datasets.

Findings

AutoMAT identified a titanium alloy 8.1% less dense and 13.0% stronger than Ti-185.

AutoMAT discovered a high-entropy alloy with 28.2% higher yield strength.

AutoMAT reduces alloy discovery time from years to weeks.

Abstract

Alloy discovery is constrained by vast compositional spaces, competing objectives, and prohibitive experimental costs. Although simulations and machine learning have each accelerated parts of this process, unifying scientific knowledge, scalable search, and experimental confirmation into a data-efficient workflow remains challenging. Here, we present AutoMAT, a hierarchical autonomous framework spanning ideation to experimental validation. Integrating large language models, automated CALPHAD simulations, residual-learning-based correction, and AI-guided optimization, AutoMAT translates design targets into candidate alloys, refines compositions through closed-loop computational search, and validates results experimentally without hand-curated datasets. Targeting lightweight, high-strength alloys, AutoMAT identifies a titanium alloy 8.1% less dense and 13.0% stronger than the aerospace benchmark Ti-185, achieving the highest specific strength among benchmarked systems. In a second case, AutoMAT discovers a high-entropy alloy with 28.2% higher yield strength than the baseline while preserving high ductility. AutoMAT compresses alloy discovery from years to weeks, establishing a generalizable route toward autonomous materials design.