用多智能体系统提升工程设计中需求到代码的连贯生成能力
Agentic Large Language Models for Conceptual Systems Engineering and Design
- 构建九角色多智能体协同设计，通过图结构整合需求与物理模型
- 多智能体生成更细粒度设计图（平均5-6节点），但代码兼容性不足50%
- 推理优化模型能更好判断流程完成，但需求覆盖仍低于20%
早期工程设计涉及复杂迭代推理，现有大语言模型工作流难以保持任务连续性并生成可执行模型。本文评估结构化多智能体系统（MAS）在需求提取、功能分解和仿真代码生成方面是否优于简单双智能体系统（2AS）。以一份技术规格书中的太阳能净水系统为应用目标，提出设计状态图（DSG），一种可序列化的JSON格式，将需求、物理实现与基于Python的物理模型打包为图节点。九角色MAS持续构建与优化DSG，而2AS则简化为生成-反思循环。共开展60次实验（2种LLM：Llama 3.3 70B vs 推理优化版DeepSeek R1 70B，各2种代理配置，3种温度，5个随机种子）。评估指标包括JSON有效性、需求覆盖率、实体存在性、代码兼容性、流程完成度、运行时长与图规模。所有实验中，两种系统均保持100% JSON完整性与实体标记正确性。需求覆盖率始终低于20%。代码兼容性在特定2AS设置下达100%，但MAS平均低于50%。仅推理优化模型稳定识别流程完成。使用DeepSeek R1 70B时，MAS生成更细粒度的DSG（平均5-6节点），而2AS出现模式坍缩。结构化多智能体提升了设计细节，推理优化模型提高了完成率，但需求覆盖与编码保真度仍存显著缺口。
原文摘要 · Abstract (English)
Early-stage engineering design involves complex, iterative reasoning, yet existing large language model (LLM) workflows struggle to maintain task continuity and generate executable models. We evaluate whether a structured multi-agent system (MAS) can more effectively manage requirements extraction, functional decomposition, and simulator code generation than a simpler two-agent system (2AS). The target application is a solar-powered water filtration system as described in a cahier des charges. We introduce the Design-State Graph (DSG), a JSON-serializable representation that bundles requirements, physical embodiments, and Python-based physics models into graph nodes. A nine-role MAS iteratively builds and refines the DSG, while the 2AS collapses the process to a Generator-Reflector loop. Both systems run a total of 60 experiments (2 LLMs - Llama 3.3 70B vs reasoning-distilled DeepSeek R1 70B x 2 agent configurations x 3 temperatures x 5 seeds). We report a JSON validity, requirement coverage, embodiment presence, code compatibility, workflow completion, runtime, and graph size. Across all runs, both MAS and 2AS maintained perfect JSON integrity and embodiment tagging. Requirement coverage remained minimal (less than 20%). Code compatibility peaked at 100% under specific 2AS settings but averaged below 50% for MAS. Only the reasoning-distilled model reliably flagged workflow completion. Powered by DeepSeek R1 70B, the MAS generated more granular DSGs (average 5-6 nodes) whereas 2AS mode-collapsed. Structured multi-agent orchestration enhanced design detail. Reasoning-distilled LLM improved completion rates, yet low requirements and fidelity gaps in coding persisted.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。