用自然语言生成并验证相场模拟，自动完成从输入到结果的全流程。
AutoMOOSE: An Agentic AI for Autonomous Phase-Field Simulation
- 六类智能体协同生成、执行、分析和对抗性验证相场模拟。
- 25项任务中19次成功模拟，15项符合物理规律且通过严格检验。
- 适合材料模拟研究者，可大幅降低相场建模门槛。
相场建模将热力学与动力学关联至微结构演化，但多物理场框架MOOSE需专业知识构建输入、管理仿真、诊断失败并验证结果。我们提出AutoMOOSE，一个开源多智能体框架，仅需自然语言提示即可统筹仿真全生命周期。六个专精智能体——架构师、输入生成器、运行器、评审员、可视化器及基于物理的质疑者——协同生成、执行、分析并对抗性测试仿真，以守恒律、渐近极限和标度关系为依据。在两个领域验证：非守恒铜晶粒生长（Allen-Cahn动力学）和守恒Fe-Cr自旋分解（Cahn-Hilliard动力学）。针对前瞻性设定的25任务基准（涵盖温度、晶粒数、分辨率与模型形式），AutoMOOSE为全部25项生成有效输入，完成19次可测量粗化模拟，并产出15项满足Burke-Turnbull动力学（R² ≥ 0.90）且通过质疑者检验的结果。失败源于两个可识别的生成器缺陷。1000次模拟的集合经有限尺寸外推后，恢复激活能至0.228 eV（真实值0.230 eV），误差小于1%。在守恒域，代理生成的基于CALPHAD的Fe-Cr模拟使质量漂移控制在6.3×10⁻⁶以内，自由能耗散至稳定平台并趋近平衡共轭线。受控消融实验显示，完整流程将随机生成的3-7次成功（8次中）转化为全部8次一致成功。
原文摘要 · Abstract (English)
Phase-field modeling links thermodynamics and kinetics to microstructural evolution, but multiphysics frameworks such as MOOSE require expertise to construct inputs, manage campaigns, diagnose failures, and validate results. We introduce AutoMOOSE, an open-source multi-agent framework that orchestrates the simulation lifecycle from a single natural-language prompt. Six specialized agents--Architect, Input Writer, Runner, Reviewer, Visualization, and a physics-grounded Skeptic--generate, execute, analyze, and adversarially test simulations against conservation laws, asymptotic limits, and scaling relations. We validate AutoMOOSE in two domains: non-conserved copper grain growth governed by Allen-Cahn dynamics and conserved Fe-Cr spinodal decomposition governed by Cahn-Hilliard dynamics. On a prospectively specified 25-task grain-growth benchmark spanning temperature, grain count, resolution, and model formulation, AutoMOOSE generates valid inputs for all 25 tasks, completes 19 simulations with measurable coarsening, and delivers 15 results that satisfy Burke-Turnbull kinetics ($R^2 \geq 0.90$) and survive Skeptic falsification. The failures trace to two identifiable generator defects. An ensemble of 1000 simulations recovers the prescribed activation energy to within 1% after finite-size extrapolation ($Q_\infty = 0.228$ eV versus $0.230$ eV). In the conserved domain, an agent-generated CALPHAD-based Fe-Cr simulation limits relative mass drift to $6.3 \times 10^{-6}$, dissipates free energy to a stable plateau, and evolves toward the equilibrium tie-line. Controlled ablations show that the full pipeline converts stochastic raw generation--3-7 successful tasks out of 8 across repeated trials--into consistent success on all 8 tasks. AutoMOOSE therefore provides a practical route from natural-language specification to reproducible, physics-validated phase-field simulation campaigns.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。