发表机构
Universidade Federal de Pernambuco (UFPE)（伯南布哥联邦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出多智能体自校正工作流GADR，从原始会议转录文本提取架构决策并生成Nygard格式ADR，经评估其效果优于零样本、少样本基线，还探讨了RAG丰富化的权衡及自动架构文档可追溯性问题。
AI 中文摘要
现有基于大语言模型（LLM）的架构决策记录（ADR）生成方法存在一个关键且未被充分研究的假设：输入已具备合理的结构化形式。但在实践中，架构决策产生于非正式、嘈杂的会议中，决策内容隐含、碎片化且与无关对话交织，正是这种情况下，单次提示会导致性能下降。本文提出GADR，一种多智能体、自校正的工作流，可从原始会议转录文本中提取架构决策并生成Nygard格式的ADR草稿。一项可行性研究包含5个真实项目会议转录文本、4位高级架构师的专家评审以及15名学生的评估，初步证据表明，该智能体工作流能捕获多数专家识别的决策，生成的草稿被参与者认为清晰且有用，在稳定性和结构合规性上优于零样本和少样本基线方法。该研究还探讨了基于检索增强生成（RAG）的丰富化在提升ADR深度的同时，存在偏离转录文本内容的风险这一未被充分研究的权衡，提出了自动架构文档可追溯性的开放性问题，值得社区关注。
英文摘要
Existing LLM-based approaches to Architecture Decision Record (ADR) generation share a critical and largely unexamined assumption: that input is already reasonably structured. In practice, architectural decisions emerge from informal, noisy meetings where choices are implicit, fragmented, and entangled with off-topic dialogue, precisely the conditions under which single-pass prompting degrades. This paper presents GADR, a multi-agent, self-correcting workflow that extracts architectural decisions from raw meeting transcriptions and generates Nygard-formatted ADR drafts. A feasibility study comprising five real project meeting transcripts, expert review by four senior architects, and evaluation by fifteen students provides initial evidence that the agentic workflow captures most expert-identified decisions and produces drafts participants found clear and useful, outperforming zero-shot and few-shot baselines in stability and structural adherence. The study also addresses the underexplored trade-off of RAG-based enrichment improving ADR depth while simultaneously risking transcript-unfaithful content, raising open questions about traceability in automated architectural documentation that we believe is worth the community's attention.
