# GADR: Gathering Architecture Decision Records from Meeting Transcriptions

arXiv: https://arxiv.org/abs/2608.17694 · HTML: https://mlsanity.com/paper/2608.17694/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 5 of 5)

- [Do Multilingual LLMs Think In English?](https://mlsanity.com/paper/2502.15603/) (2025)
- [Can LLMs Generate Architectural Design Decisions? -An Exploratory Empirical study](https://mlsanity.com/paper/2403.01709/) (2024)
- [DRAFT-ing Architectural Design Decisions using LLMs](https://mlsanity.com/paper/2504.08207/) (2025)
- [Empirical Research on Utilizing LLM-based Agents for Automated Bug Fixing via LangGraph](https://mlsanity.com/paper/2502.18465/) (2025)
- [What rationales drive architectural decisions? An empirical inquiry](https://mlsanity.com/paper/2309.14164/) (2023)

## Abstract (arXiv)

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.