验证驱动的闭环多智能体大语言模型框架：面向符合代码规范的结构设计
Verication-driven closed-loop multi-agent large language modelframework for code-compliant structural design
浏览论文内容
中文总结 AI 辅助
本研究提出验证驱动的闭环多智能体LLM框架，通过耦合有限元验证系统与双节点结构提升结构设计的代码合规性，开源基准与脚本，性能提升显著且具可复现性。
中文摘要 AI 辅助
多智能体大语言模型（LLM）系统已应用于结构设计领域，但多数采用一次性生成模式，且无法验证输出结果，因此不适用于安全关键场景。本框架不依赖LLM的自我修正，而是将基于物理的外部验证器反馈注入闭环修复循环。该框架耦合了三层有限元验证系统与双节点结构：节点1将代码违规转化为硬性修复约束，节点2将四维质量评分转化为安全优先的软性约束，检索增强代码库使所有违规可追溯至根源。在多种结构类型及44个案例中，代码合规性从56.8%提升至98.6%，综合评分从63.8提升至71.4（p<0.000001），仅需约5.8%的额外计算资源。任一节点缺失都会导致性能下降，且在测试的两种主干LLM中合规性无明显变化，表明改进源于外部验证器而非LLM主干。本研究将44个案例基准及所有实验脚本开源，以支持可复现性。
英文摘要
Multi-agent large language model(LLM)systems are applied to structural design,yet most use one-shot generation and cannot verify their output,leaving themill-suited to safety-critical tasks.Rather than trusting LLM self-correction,thisframework injects feedback from an external physics-based verier into a closedrepair loop.The framework couples a three-layernite-element verication systemwith a dual-node loop.Node 1 turns code violations into hard repair constraints,Node 2 turns a four-dimensional quality score into safety-rst soft constraints,and a retrieval-augmented code base makes every violation traceable to a clause.Overve structure types and 44 cases,code compliance rises from 56.8%to 98.6%and the composite score from 63.8 to 71.4(p<0.000001),using about 5.8%lessmaterial.Removing either node degrades performance,and compliance does notchange detectably across the two backbone LLMs tested,indicating that it ishere attributed to the external verier rather than the model.The framework,the 44-case benchmark and all experiment scripts are released as open source forreplicability.
发表机构
- College of Civil Engineering, Fuzhou University（福州大学土木工程学院）
机构由 AI 辅助整理，请以论文原文为准。
