A Novel Multi-Agent Architecture to Reduce Hallucinations of Large Language Models in Multi-Step Structural Modeling

2026-03-08

AI Summary

This work addresses the challenge of hallucination and error accumulation in large language models during multi-step structural modeling. To mitigate these issues, the authors propose a novel multi-agent collaborative framework that decomposes the modeling process into five distinct phases—problem parsing, planning, geometric construction, load assignment, and code generation—each handled by specialized agents working in parallel. This architecture autonomously generates OpenSeesPy scripts while effectively suppressing hallucinations and error propagation over long sequences of operations. Evaluated on 20 frame structures, the approach achieves 100% accuracy in 18 cases and 90% in the remaining two, demonstrating significant improvements in accuracy, efficiency, and scalability for structural modeling tasks.

Technology Category

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

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Large language models (LLMs) such as GPT and Gemini have demonstrated remarkable capabilities in contextual understanding and reasoning. The strong performance of LLMs has sparked growing interest in leveraging them to automate tasks traditionally dependent on human expertise. Recently, LLMs have been integrated into intelligent agents capable of operating structural analysis software (e.g., OpenSees) to construct structural models and perform analyses. However, existing LLMs are limited in handling multi-step structural modeling due to frequent hallucinations and error accumulation during long-sequence operations. To this end, this study presents a novel multi-agent architecture to automate the structural modeling and analysis using OpenSeesPy. First, problem analysis and construction planning agents extract key parameters from user descriptions and formulate a stepwise modeling plan. Node and element agents then operate in parallel to assemble the frame geometry, followed by a load assignment agent. The resulting geometric and load information is translated into executable OpenSeesPy scripts by code translation agents. The proposed architecture is evaluated on a benchmark of 20 frame problems over ten repeated trials, achieving 100% accuracy in 18 cases and 90% in the remaining two. The architecture also significantly improves computational efficiency and demonstrates scalability to larger structural systems.

Problem

• large language models
• hallucinations
• multi-step structural modeling
• error accumulation
• structural analysis

Innovation

• multi-agent architecture
• hallucination reduction
• structural modeling
• OpenSeesPy automation
• large language models