通用框架之外，CAE仿真智能体还需要什么？

中文摘要 AI 辅助

计算机辅助工程（CAE）仿真是工程领域规模最大、要求最高的领域之一，设置OpenFOAM、FEniCS或COMSOL等求解器需要真正的专业知识。大语言模型（LLM）智能体有望将自然语言请求转化为可运行的仿真，近期的CAE智能体加入了仿真专用机制：多智能体分解、领域检索和脚本化反思。这些机制适用于弱基础模型；现代框架已提供多轮推理、工具使用和执行反馈。本文探究CAE仿真智能体在通用框架之外仍需什么。在信息访问和修复预算固定的情况下，单智能体框架的性能与多智能体专用系统相当或更优（FoamBench为96.4%，多智能体系统为88.2%）。消融实验将此归因于框架已具备的能力：执行反馈修复使FoamBench从无修复轮次的71.8%提升至96.4%，而脚本化反思无增益。唯一仍有帮助的输入是作为求解器教程提供的领域知识，这是观测到的最大增益（从80.9%提升至96.4%）。

英文摘要

Computer-aided engineering (CAE) simulation is among the largest and most demanding areas of engineering, where setting up a solver such as OpenFOAM, FEniCS, or COMSOL takes real expertise. Large language model (LLM) agents promise to turn a natural-language request into a working simulation, and recent CAE agents add simulation-specific machinery: multi-agent decomposition, domain retrieval, and scripted reflection. That machinery suited weak base models; modern harnesses already supply multi-turn reasoning, tool use, and execution feedback. We ask what a CAE simulation agent still needs beyond a generic harness. With information access and repair budget held fixed, a single-agent harness matches or beats multi-agent specialized systems (FoamBench 96.4\% vs.\ 88.2\%). Ablations trace this to capabilities the harness already provides: execution-feedback repair lifts FoamBench from 71.8\% with no repair round to 96.4\%, while scripted reflection adds nothing. The one input that still helps is domain knowledge supplied as solver tutorials, our largest measured gain (80.9\% to 96.4\%).

发表机构

• DP Technology（达梦科技）
• School of Astronautics, Beihang University（北京航空航天大学宇航学院）
• AI for Science Institute（人工智能科学研究院）

机构由 AI 辅助整理，请以论文原文为准。