MechFoundry:对真实物体进行工程分析与优化的智能体循环
MechFoundry: An agentic loop that poses and performs engineering analyses and optimization of real-world objects
Xue-Ling Luo · Marco Conte · Peter Yichen Chen · Nikolaos Bouklas
中文摘要
AI 智能体可借助编译器或测试套件自动完成软件工程,但在工程分析中,计算前的建模、使用方式判断、支撑与载荷施加位置、各部件材料选择等步骤缺乏易验证的检查,通常需人类专家逐物体决策与评判。MechFoundry 是一个与定制软件耦合的智能体循环,无需人工介入即可自动完成真实物体的结构分析:从物体的文本描述生成形状,提出与其使用方式相关的载荷工况,为各部件分配材料,求解非线性结构响应,并针对所承载荷改进设计。基于自适应八叉树、无需贴合表面的可微 GPU 求解器,实现了从形状生成到仿真与优化的衔接。在 50 个日常与工程物体上,智能体平均用 6.5 分钟、1.3 美元完成一个载荷工况的提出与求解。由于没有测试套件可供对照,研究让语言模型评审员对每次会话打分,作为智能体工程判断在何处成立、何处失败的初步指示。
关键要点
- 01工程分析中计算前的建模与载荷设定缺乏可验证检查,通常依赖人类专家逐物体决策。
- 02MechFoundry 从文本描述自动生成形状、设定载荷、分配材料并求解非线性结构响应。
- 03基于自适应八叉树的可微 GPU 求解器无需贴合表面,衔接形状生成与仿真优化。
- 0450 个物体上平均 6.5 分钟、1.3 美元完成一个载荷工况的提出与求解。
- 05缺乏测试套件,改用语言模型评审员打分,初步指示工程判断的成败边界。
解读
尚无解读。
原始英文摘要
arXiv:2611.14571v1 Announce Type: cross Abstract: AI agents can automate software engineering because a compiler or a test suite checks that the code does what the user or the agent intended. In engineering analysis, however, the steps that precede the computation have few easily verifiable checks: modeling a design or an object, deciding how it is used, where supports and loads are applied, and what material each part is made of. A human expert therefore makes these decisions, carries out the steps, and judges the result, one object at a time. We present MechFoundry, an agentic loop coupled with bespoke software that automates structural analyses of real-world objects without a human in the loop. From an object's lexical description, it generates a shape, poses a loading case relevant to how the object is used, assigns a material to each part, solves the nonlinear structural response, and improves the design against the loads it carries. A differentiable GPU solver built on an adaptive octree that need not conform to the surface enables the transition from shape generation to simulation and optimization. Across 50 everyday and engineering objects, the agent posed and solved a loading case in 6.5 minutes and for US$1.3 per object on average. Without a test suite to check against, we had language-model reviewers grade each session, as a first indication of where the agent's engineering judgment holds and where it fails.