Agentic Large Language Models for Automated Structural Analysis of 3D Frame Systems
Ziheng Geng, Ian Franklin, Santiago Martinez, Jiachen Liu, Yunhe Zhao, Minghui Cheng
Why It Matters
What makes this one worth your time
This work could significantly streamline structural engineering processes, making them more efficient and accessible through natural language interfaces.
A novel framework for automating 3D structural analysis using agentic LLMs.
Summary
The paper presents a framework for using agentic large language models to automate the structural analysis of 3D frame systems, addressing challenges in geometric representation and reasoning.
Key contributions
- Development of a framework for automated structural analysis of 3D frames from natural language inputs.
- Introduction of a multi-agent pipeline that includes various specialized agents for problem analysis, geometry assembly, and code generation.
- Demonstration of high accuracy in analysis through empirical evaluation on representative 3D frames.
Notable insights
- The use of a 2D projection to represent irregular 3D frames is a clever approach to simplify complex geometric challenges.
- The multi-agent pipeline effectively decomposes the problem into manageable tasks, enhancing modularity and coordination.
Possible limitations
- Potential challenges in scaling the framework to more complex or irregular structures are not addressed.
- Not stated in the abstract.
Abstract
arXiv:2606.06525v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have emerged as powerful foundation models with strong reasoning capabilities across domains. Beyond reactive text generation, agentic LLMs enable autonomous workflow execution through modular task decomposition and coordinated tool use. In structural engineering, recent efforts have developed agentic LLMs for automated analysis of plane frames. However, their extension to 3D frames remains underexplored due to challenges in irregular geometric representation, topological consistency, and long-horizon reasoning. This paper proposes an agentic LLM framework for automated structural analysis of 3D frames from natural language inputs. Irregular 3D frames are represented by projection onto a 2D plan, where orthogonal gridlines define spatial coordinates and a matrix of number of stories encodes vertical extrusion of each grid cell. Building on this representation, the framework establishes a multi-agent pipeline: a problem analysis agent parses input into structured JSON; a floor decomposition agent derives the spatial layout of each floor; the 3D geometry is assembled by node, girder, slab, and column agents; support and load agents assign boundary and loading conditions, and code translation agents generate executable SAP2000 script. Evaluated on ten representative 3D frames, the proposed framework achieves an average accuracy of 90% across repeated trials, demonstrating consistent and reliable performance.