使用生成AI从历史工作项中恢复软件架构意图：一项混合方法行业案例研究

中文摘要 AI 辅助

软件架构通常仅部分被代码捕获，而大部分设计意图存在于不断演变的项目工件中。在敏捷项目中，工作项、用户故事及相关跟踪文档保留了该意图的宝贵痕迹，但它们很少支持直接的架构分析。本研究调查了使用基于大语言模型（LLM）的流程从历史敏捷工作项中恢复C4架构图的方法。该半自动五步工作流采用提示链、双向可追溯性和思维链推理，将非结构化的Azure DevOps工作项转换为可视化工件。在两个行业项目上进行评估时，我们采用混合方法设计，将定性专家访谈与定量稳定性分析相结合。从业者认为生成的架构基线准确且对系统理解非常有用。由于严格受输入数据约束，这些工件反映了记录的意图，因此在与实现的实际情况对比时，能揭示出差异和架构漂移。定量而言，该工作流对架构实体表现出高稳定性，但对实体间关系的稳定性较低，且相对方差会在各生成步骤中累积。所提出的工作流证明了基于开发过程工件的LLM辅助架构恢复的实际可行性。

英文摘要

Software architecture is often only partially captured in code, while much of the design intent lives in evolving project artifacts. In agile projects, work items, user stories, and related tracking documents preserve valuable traces of that intent, but they rarely support direct architectural analysis. This work investigates the recovery of C4 architecture diagrams from historical agile work items using an LLM-based pipeline. The semi-automatic five-step workflow employs a prompt chain, bidirectional traceability, and Chain-of-Thought reasoning to transform unstructured Azure DevOps work items into visual artifacts. Evaluated on two industry projects, we use a mixed-methods design combining qualitative expert interviews with a quantitative stability analysis. Practitioners perceive the generated architectural baselines as accurate and highly useful for system comprehension. Strictly bound by their input data, the artifacts mirror the documented intent, thereby surfacing discrepancies and architectural drift when compared to the implemented reality. Quantitatively, the workflow exhibits high stability for architectural entities but lower stability for their relationships, with relative variance compounding across generation steps. The proposed workflow demonstrates the practical viability of LLM-assisted architectural recovery based on development process artifacts.

补充信息

DOI

10.1145/3843775.3844549