[论文解读] AutoMOOSE: An Agentic AI for Autonomous Phase-Field Simulation

Sukriti Manna, Henry Chan+1 more|arXiv (Cornell University)|Mar 22, 2026

Solidification and crystal growth phenomena被引用 0

一句话总结

AutoMOOSE 是一个开源的具备代理能力的框架，能够从自然语言提示中自主编排完整的 MOOSE 相场仿真工作流，包括输入生成、执行、故障恢复和分析。

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.

研究动机与目标

• 展示从自然语言意图到端到端的 MOOSE 相场仿真自主编排。
• 通过引入基于代理的工作流管理，消除手动输入文件构造和迭代调试。
• 提供一个与物理无关的插件架构，以在不修改核心的情况下扩展到新的相场形式。
• 通过自描述的 provenance 与结构化记录，确保可重复性和符合 FAIR 数据原则。
• 在四温铜晶粒生长基准上展示端到端验证，具备自主收敛恢复能力。

提出的方法

• 定义一个五代理管线（架构师 Architect、输入撰写者 Input Writer、运行器 Runner、评审 Reviewer、可视化 Visualization），将自然语言提示转化为经验证的 MOOSE 输入文件并进行并行扫描。
• 使用一个模块化的两函数插件契约（generate_input、parse_results）以将物理细节与编排分离。
• 通过将收敛失败路由给 Reviewer 来实现自主故障诊断和修正，Reviewer 调整参数并重新生成输入。
• 在自包含的目录中捕获完整的运行溯源，并使用结构化元数据以满足 FAIR 数据原则。
• 在四温铜多晶粒生长基准上进行验证，自治恢复动力学与 Arrhenius 活化能，无需人工验证。

Figure 1: AutoMOOSE agentic pipeline. Five claude-sonnet-4-20250514 agents ( $f_{1}$ – $f_{5}$ ) transform a natural-language prompt into a completed MOOSE phase-field simulation. Architect ( $f_{1}$ ) parses the user prompt and constructs the structured simulation plan $\mathcal{P}$ (Eq. ( 9 )), en

实验结果

研究问题

• RQ1 代理 AI 是否能够从自然语言合成正确的 MOOSE 输入文件并自主执行完整的相场仿真？
• RQ2 自主故障恢复（时间步、网格、容限）是否能在无人工干预的情况下收敛到有效结果？
• RQ3 自治工作流在并行温度扫描中的表现如何，能否复现已知的动力学规律和 Arrhenius 参数？
• RQ4 管线是否足够模块化，能够通过插件扩展到其它相场形式？

主要发现

• 管线能够自主生成与人工参考高块匹配的合成句法有效的 MOOSE 输入（12 个块中有 6 块完全匹配，4 块功能等价）。
• 四个并行运行比串行执行实现 1.8× 的时钟速度提升。
• 端到端的一致性检查恢复了预期的动力学和 Arrhenius 行为，对于 T≥600 K 的晶粒粗化 R^2 在 0.90 至 0.95 之间。
• 在相同网格和参数下，Recovered Arrhenius 活化能 Q_fit = 0.296 eV 与给定 Q = 0.23 eV 一致（并且与人工参考运行相匹配）。
• 三种收敛失败类别在单次修正循环内自动诊断并解决。
• 每次运行都产生自描述的 provenance 记录，编码仿真计划字段和执行元数据。

Figure 2: AutoMOOSE run directory structure. Each run directory is timestamped and self-contained, comprising: grain_growth.i (complete MOOSE input file), grain_growth.csv (tabulated grain count time series $N(t)$ , Eq. ( 18 )), run.log (full solver stdout), metadata.json (structured provenance reco