用智能代理让工程师轻松运行复杂多物理场模拟。
Deploying Frontier Agentic Technology in MOOSEnger, a Multiphysics-Capable AI Assistant
- 构建本地化智能体，自动检索、验证并学习仿真流程。
- 在8类工程问题上成功率达90%，远超无智能体基线模型。
- 适合需要高效复现多物理场仿真的科研与工程人员。
多物理场有限元框架MOOSE是用于构建多物理场仿真应用的开源平台，但其使用需专业技能，对多数领域科学家构成障碍。本文在爱达荷国家实验室（INL）开发的领域专用智能代理MOOSEnger基础上，引入聚焦本地部署模型的集成框架。该框架使智能体具备完整工作流：从MOOSE代码库中检索上下文知识，通过与仿真可执行环境交互验证和诊断输入，并将经验提取存储于持久记忆中。该系统在国家反应堆创新中心虚拟测试床（VTB）的实际工程问题上进行了演示，展示了支持真实多物理场仿真流程的潜力。此外，在扩散、纳维-斯托克斯、相场、塑性、多孔介质流动、固体力学、瞬态传热及反应堆网格生成等8类问题上，每类25个案例进行评估。结果显示，MOOSEnger-GPT-5.2成功率90%，显著优于MOOSEnger-Gemma4的76.5%；而无智能体的Gemma4与GPT-5.2基准模型分别仅达0%和5%，凸显智能体框架的关键作用。
原文摘要 · Abstract (English)
The Multiphysics Object-Oriented Simulation Environment (MOOSE) is an open-source finite-element framework for building multiphysics simulation applications. Using a multiphysics environment effectively demands specialized expertise, creating a barrier for many domain scientists and engineers. MOOSEnger, developed at Idaho National Laboratory (INL), is a domain-specific, tool-enabled AI agent built for the MOOSE Framework. This work extends MOOSEnger with a harness focused on locally-hosted models. The harness gives the agent a full pipeline: it retrieves contextual knowledge from the MOOSE repository, validates and diagnoses the resulting input through interaction with the simulation executable environment, and extracts and stores lessons in a persistent memory. The resulting framework is demonstrated on an engineering problem from the National Reactor Innovation Center Virtual Test Bed (VTB), illustrating its potential to support realistic multiphysics simulation workflows. Additionally, the agent performance is evaluated on different categories including diffusion, Navier--Stokes, phase field, plasticity, porous media flow, solid mechanics, transient heat transfer, and reactor mesh generation. Each category consists of 25 prompts/cases. We compare MOOSEnger-Gemma4 against MOOSEnger-GPT-5.2, alongside baseline Gemma4 and GPT-5.2 without agentic capabilities. MOOSEnger-GPT-5.2 shows a slight edge, achieving a 90\% success rate versus 76.5\% for MOOSEnger-Gemma4. The baseline models perform far worse, at just 5\% (GPT-5.2) and 0\% (Gemma4), underscoring the impact of the agentic harness.
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。