analiza aiqbench
This research demonstrates a multi-agent LLM framework capable of automating structural analysis for complex 3D frames from natural language inputs, achieving 90% accuracy by decomposing tasks into specialized agents for geometry assembly and code generation. The approach addresses critical gaps in handling irregular geometric representations and long-horizon reasoning, offering a scalable solution for converting text descriptions into executable SAP2000 scripts. For the tech community, this highlights the practical viability of agentic systems in bridging the gap between high-level language inputs and precise engineering domain tasks.
Agentic Large Language Models for Automated Structural Analysis of 3D Frame Systems
arXiv:2606.06525v1 Announce Type: 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.
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.
Graphics (cs.GR); Artificial Intelligence (cs.AI)
arXiv:2606.06525 [cs.GR]
(or arXiv:2606.06525v1 [cs.GR] for this version)
https://doi.org/10.48550/arXiv.2606.06525 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 294 cuvinte
Subiecte conexe
Multi-Agent Closed-Loop Reasoning for Organic Structure Elucidation from Multimodal Spectra
arXiv · 18 aug. 2026
Data Fusion and Contrastive Alignment for Unconstrained IR Molecular Structure Elucidation
arXiv · 30 iul. 2026
Agentic Large Language Models for Automated Structural Analysis of 3D Frame Systems
arXiv · 12 iun. 2026
Article: The AI Productivity Paradox in Test Automation: Moving beyond Structural Validation to Perception and Intent
InfoQ · 1 iun. 2026