VFEAgent: A Multimodal Agent Framework for End-to-End Automated Finite Element Analysis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918528304545792 |
|---|---|
| author | Zhang, Jiachen Lao, Junyi Liu, Chenghao Liu, Siyuan Wu, Shixin Zhang, Linsen Wang, Boyu Huang, Songfang |
| author_facet | Zhang, Jiachen Lao, Junyi Liu, Chenghao Liu, Siyuan Wu, Shixin Zhang, Linsen Wang, Boyu Huang, Songfang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28978 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VFEAgent: A Multimodal Agent Framework for End-to-End Automated Finite Element Analysis Zhang, Jiachen Lao, Junyi Liu, Chenghao Liu, Siyuan Wu, Shixin Zhang, Linsen Wang, Boyu Huang, Songfang Artificial Intelligence Computational Engineering, Finance, and Science 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. |
| title | VFEAgent: A Multimodal Agent Framework for End-to-End Automated Finite Element Analysis |
| topic | Artificial Intelligence Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2605.28978 |