AutoMOOSE: An Agentic AI for Autonomous Phase-Field Simulation

2026-03-21

AI Summary

This work addresses the high barrier and labor-intensive nature of traditional phase-field materials simulations, which typically require expert intervention for input preparation, error debugging, and result extraction. The authors propose the first autonomous simulation framework based on multi-agent collaboration, capable of fully automating input generation, parameter sweeps, fault recovery, and result validation through natural language instructions. The framework employs a five-agent architecture, modular plugin design, and the Model Context Protocol (MCP) to enable scalable, interoperable parallel workflows, while integrating FAIR-compliant data provenance. Evaluated on a copper grain growth benchmark, the system autonomously produced high-fidelity input files, achieved a 1.8× acceleration in simulation throughput, yielded kinetic parameters with R² values of 0.90–0.95, exhibited minimal activation energy error, and successfully diagnosed and repaired three common runtime failures without human intervention.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

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.

Problem

• phase-field simulation
• MOOSE
• multiphysics simulation
• input file generation
• simulation automation

Innovation

• agentic AI
• phase-field simulation
• multi-agent orchestration
• Model Context Protocol
• autonomous simulation