A Lightweight Multi-Agent Framework for Automated Concrete Barrier Design

2026-06-10

AI Summary

This study addresses the inefficiency of manual iterative design in reinforced concrete crash barriers and the challenge of simultaneously accounting for nonlinear mechanical behavior and AASHTO-LRFD code constraints. To overcome these limitations, the authors propose a lightweight, multi-agent collaborative “generate–evaluate–optimize” closed-loop framework built upon the AutoGen platform. The approach integrates a small-scale large language model (8B parameters), embedded structural engineering rules, and a compliance verification mechanism, achieving over 98% design accuracy while significantly reducing computational costs. The findings demonstrate that, in highly constrained engineering tasks, domain-knowledge-guided small models can outperform much larger general-purpose models, thereby challenging the assumption of a necessary positive correlation between model scale and engineering performance and enhancing the practicality and reliability of AI in civil engineering applications.

Abstract

The design of reinforced concrete highway barriers is a safety-critical process that requires strict compliance with regulatory provisions such as the AASHTO-LRFD bridge design guidelines. Current engineering practice relies heavily on manual, iterative, and heuristic calculations to satisfy complex nonlinear material and mechanics constraints. Although Large Language Models (LLMs) demonstrate strong generative capabilities, their direct application to structural engineering remains limited by hallucination risks and insufficient physical grounding. To address these challenges, this study proposes a novel "generation-evaluation-optimization" closed-loop framework for automated concrete barrier design using the multi-agent orchestration capabilities of AutoGen. Experimental results demonstrate that the proposed agentic framework achieves over 98% design accuracy, significantly outperforming standalone general-purpose LLMs. More importantly, the study reveals that design performance is not necessarily correlated with model scale, where an 8B-parameter lightweight model could outperform unconstrained 631B-parameter flagship models. This finding highlights the potential to substantially reduce computational costs while improving the accessibility of AI-assisted engineering tools for industry applications. The source code for the proposed multi-agent design framework is available at the project GitHub repository: https://github.com/MXY820/barrier-design. Keywords: Structural Engineering; Multi-Agent Systems; Large Language Models; Concrete Barrier Design; AutoGen; Design Automation.

Problem

• Structural Engineering
• Concrete Barrier Design
• Large Language Models
• Design Automation
• Multi-Agent Systems

Innovation

• Multi-Agent Systems
• Design Automation
• Large Language Models
• Concrete Barrier Design
• AutoGen