研究评估：智能体能否可靠生成自动化 PDE 仿真的完整规格说明
From 1D Benchmarks to Complex 3D Geometries: Can Agents Reliably Specify Problems for Automated PDE Simulation?
把工程需求变成 PDE 仿真，纯模型只有 82.5% 能做对，这篇论文加了科学检查和澄清机制后做到 98.3%，做仿真自动化的可以看看它的流程设计。
arXiv 论文 2610.41267 研究智能体能否把工程需求转成可执行的 JSON 仿真规格，涵盖几何创建、网格划分、PDE 求解与结果导出。在 120 个模板相关请求上，完整工作流达到 98.3% 的首轮正确率，比 schema 辅助单轮的 92.5% 高 5.8 个百分点，比纯模型方案 82.5% 高 15.8 个百分点。工作流结合模型抽取、确定性科学检查、显式澄清与验证过的局部补丁，在 42 个需澄清或拒绝的请求中零误判为就绪。下游测试覆盖 1D 到 3D、稳态与非稳态、线性与非线性问题，包括三维机翼的流动与弹性力学，12 个真实用户到结果测试中有 9 个（75.0%）全流程成功。
From 1D Benchmarks to Complex 3D Geometries: Can Agents Reliably Specify Problems for Automated PDE Simulation?
Turning an engineering request into a simulation requires consistent geometry, physics, boundary conditions, and numerical settings. Recent agent-assisted systems automate simulation setup, but successful execution alone does not establish whether the specification preserves the intended problem or correctly handles missing information. We study whether agents can reliably construct complete executable JSON specifications for automated geometry creation, meshing, PDE solving, and result export. Our workflow combines model extraction with deterministic scientific and capability checks, explicit clarification, and validated local patches that preserve unrelated accepted fields. We evaluate specification correctness, execution completion, and numerical verification separately. On 120 template-related requests, the full workflow achieves 98.3% correct first-turn specification and decision outcomes, compared with 92.5% for schema-assisted single shot and 82.5% for model-only: gains of 5.8 and 15.8 percentage points, respectively. It makes no false-ready decisions among the 42 requests requiring clarification or rejection. Component ablations identify contributions from scientific checks and conditional repair. Separate downstream studies cover 1D, 2D, and 3D steady and unsteady, linear and nonlinear problems, including flow and elasticity with complex three-dimensional wing geometries. A 30-case gallery demonstrates automated execution from retained JSON specifications, while 9 of 12 selected live user-to-results tests achieve joint specification, execution, export, and numerical-reference success (75.0%). These results support traceable, engineer-reviewed simulation assistance within the tested scope, while fresh-response regressions identify consistency as a priority for further improvement.