AutoMOOSE: AI Chef for New Materials express
Creating a new material, like a tough alloy, requires thousands of computer experiments. Usually, a scientist manually writes instructions and hunts for errors. AutoMOOSE is a robotic kitchen: say 'I want a light and strong metal,' and five software chefs whip up a recipe, launch the synthesis, and adjust if something goes wrong.
In a test on copper grain growth, AutoMOOSE showed accuracy nearly matching an expert, and corrected three typical errors without human help. Grain growth is driven by entropy and determines strength. The approach is universal: from carbon composites to semiconductors, based on the standard model of microstructure.
Original abstract
as written by the authors arXiv:2603.20986
Multiphysics simulation frameworks such as MOOSE provide rigorous engines for phase-field materials modeling, yet adoption is constrained by the expertise required to construct valid input files, coordinate parameter sweeps, diagnose failures, and extract quantitative results. We introduce AutoMOOSE, an open-source agentic framework that orchestrates the full simulation lifecycle from a single natural-language prompt. AutoMOOSE deploys a five-agent pipeline in which the Input Writer coordinates six sub-agents and the Reviewer autonomously corrects runtime failures without user intervention. A modular plugin architecture enables new phase-field formulations without modifying the core framework, and a Model Context Protocol (MCP) server exposes the workflow as ten structured tools for interoperability with any MCP-compatible client. Validated on a four-temperature copper grain growth benchmark, AutoMOOSE generates MOOSE input files with 6 of 12 structural blocks matching a human expert reference exactly and 4 functionally equivalent, executes all runs in parallel with a 1.8x speedup, and performs an end-to-end physical consistency check spanning intent, finite-element execution, and Arrhenius kinetics with no human verification. Grain coarsening kinetics are recovered with R^2 = 0.90-0.95 at T >= 600 K; the recovered activation energy Q_fit = 0.296 eV is consistent with a human-written reference (Q_fit = 0.267 eV) under identical parameters. Three runtime failure classes were diagnosed and resolved autonomously within a single correction cycle, and every run produces a provenance record satisfying FAIR data principles. These results show that the gap between knowing the physics and executing a validated simulation campaign can be bridged by a lightweight multi-agent orchestration layer, providing a pathway toward AI-driven materials discovery and self-driving laboratories.
The five AI agents in AutoMOOSE work like a well-coordinated kitchen brigade: one writes the recipe, another checks the ingredients, a third cooks, a fourth tastes, and a fifth ensures everything stays on track. And all the user needs to do is say a couple of plain-language phrases.