Automating Structural Engineering Workflows with Large Language Model Agents

2025-10-13

AI Summary

Traditional structural engineering workflows are rigid and labor-intensive, necessitating automation to improve efficiency, reliability, and consistency. Method: This paper introduces MASSE—the first multi-agent system (MAS) tailored for structural engineering—that deeply integrates a fine-tuning-free large language model (LLM)-based multi-agent framework into real-world engineering practice. MASSE autonomously executes end-to-end tasks—including design code interpretation, load calculation, and structural verification—by synergizing complex reasoning, long-horizon planning, and precise tool invocation, enabling automatic task decomposition and collaborative agent scheduling. Contribution/Results: Evaluated on real-world engineering cases, MASSE reduces expert effort from approximately two hours to several minutes while significantly enhancing computational accuracy, result consistency, and plug-and-play usability. It establishes a reusable paradigm for LLM-powered automation in domain-specific engineering applications.

Technology Category

• Multiagent Systems: Teamwork
• Machine Learning: Structured Learning
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We introduce $ extbf{MASSE}$, the first Multi-Agent System for Structural Engineering, effectively integrating large language model (LLM)-based agents with real-world engineering workflows. Structural engineering is a fundamental yet traditionally stagnant domain, with core workflows remaining largely unchanged for decades despite its substantial economic impact and global market size. Recent advancements in LLMs have significantly enhanced their ability to perform complex reasoning, long-horizon planning, and precise tool utilization -- capabilities well aligned with structural engineering tasks such as interpreting design codes, executing load calculations, and verifying structural capacities. We present a proof-of-concept showing that most real-world structural engineering workflows can be fully automated through a training-free LLM-based multi-agent system. MASSE enables immediate deployment in professional environments, and our comprehensive validation on real-world case studies demonstrates that it can reduce expert workload from approximately two hours to mere minutes, while enhancing both reliability and accuracy in practical engineering scenarios.

Problem

• Automating structural engineering workflows using multi-agent systems
• Integrating LLM agents with real-world engineering design processes
• Reducing expert workload through automated code interpretation and calculations

Innovation

• Multi-agent system automates structural engineering workflows
• LLM agents perform code interpretation and load calculations
• Training-free system reduces expert workload from hours to minutes