用多智能体框架自动规划复杂设备的零维模型拓扑，突破人工设计瓶颈。
A Multi-Agent Framework for Zero-Dimensional Reduced-Order Model Planning
- 构建图结构与优化双引擎，将经验式设计转为可计算的拓扑优化问题。
- 在4个真实系统上验证，正反向设计性能均优于传统方法。
- 适合需要全局优化和自动化设计的航空航天、能源系统研发人员。
零维降阶模型（0D ROM）是高端复杂装备多维设计流程的核心。然而当前规划依赖人工经验，限制了拓扑探索并延长迭代周期。传统优化方法如遗传算法（GA）通常仅限局部参数调优。尽管大语言模型（LLM）代理在探索大规模样本空间方面展现潜力，且链式思维（CoT）与推理-行动（ReAct）提升推理可靠性，检索增强生成（RAG）克服领域知识壁垒，但单一代理仍难以应对复杂0D ROM规划中长期且高度耦合的挑战。本文提出零维降阶模型协同规划框架（Z-COPA），采用包含符号动作图引擎（SAGE）与混合整数线性规划引导导航（MGN）优化器的多智能体架构。其核心创新在于专用图表示方法，精确编码0D流网络拓扑，将经验性规划过程转化为严谨的图结构优化问题。我们在两个真实航空发动机次级气流系统、两个IEEE电力分配重构基准及两个供水管网基准上验证了Z-COPA的正向与逆向设计能力及泛化性能。结果表明，其任务完成质量更优，在空气系统正反向设计中均取得最佳表现。Z-COPA颠覆传统0D模型规划范式，为拓展更广拓扑空间、实现高度自动化、全局最优的气动系统架构提供了新路径。
原文摘要 · Abstract (English)
Zero-dimensional reduced-order models (0D ROMs) are central to multi-dimensional design workflows for high-end complex equipment. However, the planning process currently relies on manual expertise, limiting topological exploration and prolonging iterations. Even traditional optimization methods such as Genetic Algorithms (GA) are typically confined to local parameter tuning. Although Large Language Model (LLM) agents have shown promise in exploring large sample spaces, and frameworks such as Chain of Thought (CoT) and Reason and Act (ReAct) improve reasoning reliability, while Retrieval-Augmented Generation (RAG) overcomes domain knowledge barriers, a single agent still falls short for the long-horizon and highly coupled nature of complex 0D ROM planning. This paper proposes the Zero-dimensional reduced-order model CO-Planning framework (Z-COPA), a multi-agent architecture featuring a Symbolic Action Graph Engine (SAGE) and a MILP-Guided Navigation (MGN) optimizer. Its core innovation is a dedicated graph representation method that accurately encodes the 0D flow network topology, converting the empirical planning process into a rigorous graph structure optimization problem. We validate the forward and inverse design capabilities and generalization performance of Z-COPA on two real aircraft engine secondary-air systems, two IEEE power-distribution reconfiguration benchmarks, and two water-distribution network benchmarks. The results show superior task completion quality, obtaining the best performance in both forward and reverse design of air systems. Z-COPA disrupts the traditional 0D model planning paradigm, providing a new technical approach for exploring broader topological space and achieving highly automated, globally optimal air system architectures.
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。