从杂乱会议记录中自动提取架构决策并生成规范文档。
GADR: Gathering Architecture Decision Records from Meeting Transcriptions
- 多智能体协同工作，逐步纠正错误，从原始录音中提炼决策。
- 在5个真实项目数据上，捕获率超专家识别的90%，结构更稳定。
- 适合团队做自动化文档，关注可追溯性与内容真实性的研究者。
现有基于大模型的架构决策记录（ADR）生成方法普遍假设输入已具备合理结构，但实际中架构决策常源于非正式、嘈杂的会议，决策隐含、碎片化且混杂于无关对话中，导致单次提示方法性能下降。本文提出GADR，一种多智能体自纠错工作流，可从原始会议转录文本中提取架构决策，并生成符合Nygard格式的ADR初稿。一项包含五个真实项目会议记录的可行性研究，经四位资深架构师评审及十五名学生评估，表明该流程能捕获超过90%专家识别的决策，生成的草案被参与者认为清晰且实用，显著优于零样本和少样本基线，在稳定性和结构一致性上表现更佳。研究还揭示了基于RAG增强虽提升文档深度，却可能引入脱离原文的内容，引发自动化文档中可追溯性问题，值得学界关注。
原文摘要 · Abstract (English)
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.
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。