Computational materials agents: from task demonstrations to executable scientific workflows
TL;DR
This review examines how current systems translate materials questions into computational tasks, identifies the settings in which reliability and recovery have been demonstrated, and explains why runnable calculations should be distinguished from scientifically justified conclusions.
Abstract
Computational materials modeling connects physical theory, atomistic mechanisms, and materials design, but its value depends on workflows that are specified, executed, checked, and interpreted with scientific rigor. Agents built on large language models are beginning to link materials knowledge with databases, simulation software, workflow controllers, and feedback mechanisms, enabling greater automation of computational research. However, most reported successes remain concentrated in scaffolded settings for density functional theory, molecular dynamics, and related atomistic simulations, where tasks, engines, validators, and target outputs are predefined. This review analyzes computational materials agents across three interconnected dimensions: architecture, executable workflow practices, and evaluation evidence. We examine how current systems translate materials questions into computational tasks, identify the settings in which reliability and recovery have been demonstrated, and explain why runnable calculations should be distinguished from scientifically justified conclusions. By clarifying the evidence required for traceable, reproducible, and reusable workflows, this review aims to guide the development of computational materials agents from task demonstrations to practical scientific tools.
