arXiv AI August 19, 2026 By Lucas Daniel Costa da Silva, Kiev Gama

GADR: Gathering Architecture Decision Records from Meeting Transcriptions

The paper introduces GADR, a multi‑agent, self‑correcting workflow that extracts architectural decisions from raw meeting transcriptions and produces Nygard‑formatted ADR drafts. A feasibility study using five real project transcripts, expert reviews by four senior architects, and evaluations by fifteen students shows that GADR captures most expert‑identified decisions and yields drafts that participants find clear and useful, outperforming zero‑shot and few‑shot baselines in stability and structural adherence. The study also highlights a trade‑off: RAG‑based enrichment can deepen ADR content but may introduce transcript‑unfaithful material, raising open questions about traceability in automated architectural documentation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 2

Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memory

arXiv:2606. 01385v1 Announce Type: cross Abstract: Software architecture design is a critical yet inherently complex and knowledge-intensive phase that requires balancing competing quality attributes and adapting to evolving requirements.

By Ruiyin Li, Yiran Zhang, Xiyu Zhou, Yangxiao Cai, Peng Liang, Weisong Sun, Jifeng Xuan, Zhi Jin, Yang Liu

llms rag agents

arXiv AI

Sep 4

Can LLMs Extract Architectural Design Decisions from Source Code Commits? - A Preliminary Exploratory Study

The study investigates whether large language models can extract Architectural Design Decisions (ADDs) from source code commits. Using four LLMs (Gemini 3 Pro, DeepSeek R1, Kimi K2, Qwen3) with zero‑shot and few‑shot prompting on 30 developer‑written ADDs, the authors evaluate outputs with ROUGE‑L, BLEU, METEOR, and BERTScore. Results show all models achieve a BERT‑F1 above 0.81, with few‑shot prompting slightly improving alignment, but the generated ADDs tend to be overly long, implementation‑focused, and lack the rationale behind the decisions.

By Amey Karan, Rudra Dhar, Mohamed Soliman, Karthik Vaidhyanathan

llms safety

arXiv AI

Jun 16

Beyond Correctness: Enhancing Architectural Reasoning in Code LLMs via Scalable Labeling with Agentic Judgment

arXiv:2606. 14948v1 Announce Type: cross Abstract: LLMs have substantially improved software engineering yet real-world development requires architectural understanding.

By Kirill Vasilevski (Justina), Ximing Dong (Justina), Benjamin Rombaut (Justina), Ruochen Deng (Justina), Jiahuei Lin (Justina), Arthur Leung, Dayi Lin, Boyuan Chen, Shaowei Wang, Ahmed E. Hassan

llms agents fine-tuning

arXiv AI

Jun 30

SAKE: Software Architectural Knowledge Evaluation Benchmark for Large Language Models

arXiv:2606. 29520v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used as assistants across the software development lifecycle, yet their ability to reason about software architecture remains largely unmeasured.

By Tiziano Santilli, Francesco Daghero, Mayhar Tourchi Moghaddam

llms benchmarks

arXiv AI

Jun 24

Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment

arXiv:2606. 24834v1 Announce Type: new Abstract: LLM-based dialogue assistants have become mainstream tools for software developers, yet current evaluation benchmarks focus exclusively on functional correctness.

By Ali Pourghasemi Fatideh, Wilder Baldwin, Maria Dhakal, Collin McMillan, Sepideh Ghanavati

llms agents benchmarks

arXiv Machine Learning

Oct 15

Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer

arXiv:2604.17883v2 Announce Type: replace-cross Abstract: Vibe coding turns natural-language intent into working software, but code generation alone does not give humans and agents a shared account o...

By Tianfu Wang, Zhezheng Hao, Yin Wu, Wei Wu, Haowen Yang, Linxiao Gong, Qiang Lin, Hande Dong, Nicholas Jing Yuan, Hui Xiong

agents

One email a morning, machine-written

Related stories

Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memory

Can LLMs Extract Architectural Design Decisions from Source Code Commits? - A Preliminary Exploratory Study

Beyond Correctness: Enhancing Architectural Reasoning in Code LLMs via Scalable Labeling with Agentic Judgment

SAKE: Software Architectural Knowledge Evaluation Benchmark for Large Language Models

Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment

Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer