VFEAgent: A Multimodal Agent Framework for End-to-End Automated Finite Element Analysis

Computer Science > Artificial Intelligence [Submitted on 27 May 2026] VFEAgent: A Multimodal Agent Framework for End-to-End Automated Finite Element Analysis Jiachen Zhang (1 and 2), Junyi Lao (1), Chenghao Liu (1), Siyuan Liu (1), Shixin Wu (1), Linsen Zhang (1), Boyu Wang (1), Songfang Huang (1) ((1) Peking University, (2) China Agricultural University) Finite Element Analysis (FEA) serves as the cornerstone of modern engineering design. However, its workflow is inherently complex and relies heavily on domain expertise. Although recent efforts have integrated Large Language Models (LLMs) into FEA, existing approaches face limitations in handling multimodal inputs and executing complex tasks. To address these limitations, we propose VFEAgent, an end-to-end multi-agent system designed to automate FEA modeling and simulation directly from input images and problem descriptions. Our methodology integrates two core components: (1) a multimodal vision-language multi-agent pipeline that employs ReAct-driven reasoning to extract structured FEA specifications from heterogeneous inputs and (2) a verification-first code synthesis framework, incorporating robust self-debugging and fallback mechanisms to ensure executability and physical validity. We systematically evaluated the system across various engineering mechanics scenarios. The results demonstrate that VFEAgent achieves a high success rate in generating complete and physically valid simulations, outperforming LLM-based baseline methods in reliability and correctness. These findings validate the feasibility of automating the complete FEA workflow, highlighting the framework's potential to liberate engineers from tedious manual analysis. Comments: 9 pages, 3 figures, 2 tables. Equal contribution: Jiachen Zhang and Junyi Lao. Corresponding author: Songfang Huang. Preprint Subjects: Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE) Cite as: arXiv:2605.28978 [cs.AI]   (or arXiv:2605.28978v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.28978 Focus to learn more Submission history From: Jiachen Zhang [view email] [v1] Wed, 27 May 2026 18:34:04 UTC (11,350 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.CE References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)