迈向对大型语言模型生成的微服务架构的特征刻画
Towards a Characterization of Microservice Architectures Generated by Large Language Models
浏览论文内容
中文总结 AI 辅助
本研究实证刻画了LLMs从模块化单体描述生成微服务架构的行为，发现提示策略（少样本vs零样本）比模型提供商更显著影响架构的粒度、通信密度和职责描述，为生成式架构转换提供了基线。
中文摘要 AI 辅助
大型语言模型（LLMs）越来越多地被用于软件设计任务，然而，对其所生成架构的结构和连贯性却知之甚少。特别是，LLMs在架构到架构（Architecture-to-Architecture）转换中的行为仍未得到充分理解。本研究通过实证方法，刻画了LLMs如何从模块化单体系统的自然语言描述中生成微服务架构，重点关注结构和描述性属性，而非架构正确性。我们在两个模块化单体系统上进行了受控实验，比较了使用来自OpenAI的基于GPT的模型和来自DeepSeek的模型的零样本（zero-shot）和少样本（few-shot）提示策略。生成的架构以标准化的CSV格式表示，并使用归一化指标进行评估，这些指标涵盖服务粒度、服务间通信模式、通信密度、服务隔离性和职责描述性。结果显示，系统性差异主要由提示策略而非模型提供商驱动。少样本提示始终产生更细粒度的分解，具有更低的通信密度和更详细的职责描述，而零样本提示则倾向于更粗粒度且连接更紧密的架构。本研究并非评估架构质量，而是为理解LLMs在文本驱动的架构到架构转换中的行为提供实证基线，为生成式设计工作流和混合架构推理在早期软件现代化中的未来研究提供参考。
英文摘要
Large Language Models (LLMs) are increasingly used for software design tasks, yet little is known about the structure and coherence of the architectures they produce. In particular, how LLMs behave in Architecture-to-Architecture transformations remains insufficiently understood. This study empirically characterizes how LLMs generate microservice architectures from natural language descriptions of modular monoliths, focusing on structural and descriptive properties rather than architectural correctness. We conduct controlled experiments on two modular monolith systems, comparing zero-shot and few-shot prompting strategies using GPT-based models from OpenAI and models from DeepSeek. Generated architectures are represented in a standardized CSV format and evaluated using normalized metrics capturing service granularity, inter-service communication patterns, communication density, service isolation, and responsibility descriptiveness. The results reveal systematic differences driven primarily by prompting strategy rather than model provider. Few-shot prompting consistently produces finer-grained decompositions with lower communication density and more detailed responsibility descriptions, whereas zero-shot prompting favors coarser and more tightly connected architectures. Rather than assessing architectural quality, this study provides an empirical baseline for understanding LLM behavior in text-driven Architecture-to-Architecture transformations, informing future research on generative design workflows and hybrid architectural reasoning in early-stage software modernization.
发表机构
- Federal University of Campina Grande（坎皮纳格兰德联邦大学）
机构由 AI 辅助整理，请以论文原文为准。
