A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems
Abstract
AbaqusAgent is a multi-agent framework using large language models to automate finite element analysis by converting natural language instructions into executable simulations with high success rates across diverse solid mechanics problems.
Finite element analysis (FEA) is the most important numerical approach for solid mechanics. Challenges of FEA include a steep learning curve for entry-level users and potential false simulations due to incorrect definitions of key simulation components, such as boundary conditions, load cases, and solution variables. Years of engineering experience are usually necessary for real-world problem-solving. To address these issues, we present AbaqusAgent, a multi-agent framework grounded in large language models (LLMs) for solid mechanics analyses. AbaqusAgent is developed to facilitate analysis case generation and execution using Abaqus, one of the most widely used FEA packages, by turning users' natural-language instructions into executed FEA analyses and result visualization. AbaqusAgent is composed of six agents, including interpreter, architect, input writer, runner, reviewer, and visualizer agents, encompassing all the essential pre-processing and post-processing steps of standard FEA analyses. A wide variety of 50 solid mechanics problems have been successfully validated, achieving an overall success rate of 86%. Beyond improving the efficiency of FEA for solid mechanics problems and lowering the barrier to computational mechanics education, AbaqusAgent advances the human-simulation interaction paradigm and enables integration with AI-empowered optimization and material characterization workflows. The code is available at https://github.com/LIRAM-LIN/AbaqusAgent
Community
Really interesting application of multi-agent LLM systems to a domain where mistakes are expensive: finite element analysis. AbaqusAgent decomposes the workflow into interpreter, architect, input writer, runner, reviewer, and visualizer agents, turning natural-language problem statements into Abaqus simulations and result visualizations. The reported 86% success rate across 50 solid-mechanics benchmarks suggests that agentic systems can do more than chat or code generation: they can orchestrate specialized engineering tools end to end. I especially like the built-in reviewer step, since trustworthy simulation depends as much on correct boundary conditions and load definitions as on generating runnable scripts. This could be useful for education, rapid prototyping, and AI-assisted design loops, while still requiring expert validation for high-stakes engineering decisions.
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper