# LLM-based Automated Architecture View Generation: Where Are We Now?

arXiv: https://arxiv.org/abs/2603.21178 · HTML: https://mlsanity.com/paper/2603.21178/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 63 references that are in the map.
- First posted on arXiv 22 Mar 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark](https://mlsanity.com/paper/2402.04788/) (2024)
- [GPTScore: Evaluate as You Desire](https://mlsanity.com/paper/2302.04166/) (2023)
- [Self-Preference Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2410.21819/) (2024)
- [Agents in Software Engineering: Survey, Landscape, and Vision](https://mlsanity.com/paper/2409.09030/) (2024)
- [Navigating the Complexity of Generative AI Adoption in Software Engineering](https://mlsanity.com/paper/2307.06081/) (2023)
- [Can LLMs Generate Architectural Design Decisions? -An Exploratory Empirical study](https://mlsanity.com/paper/2403.01709/) (2024)
- [Generative AI for Software Architecture. Applications, Challenges, and Future Directions](https://mlsanity.com/paper/2503.13310/) (2025)
- [Model Generation with LLMs: From Requirements to UML Sequence Diagrams](https://mlsanity.com/paper/2404.06371/) (2024)
- [From Image to UML: First Results of Image Based UML Diagram Generation Using LLMs](https://mlsanity.com/paper/2404.11376/) (2024)
- [Software Architecture Meets LLMs: A Systematic Literature Review](https://mlsanity.com/paper/2505.16697/) (2025)
- [LLMs for Generation of Architectural Components: An Exploratory Empirical Study in the Serverless World](https://mlsanity.com/paper/2502.02539/) (2025)

## Abstract (arXiv)

Architecture views are essential for software architecture documentation, yet their manual creation is labor intensive and often leads to outdated artifacts. As systems grow in complexity, the automated generation of views from source code becomes increasingly valuable. Goal: We empirically evaluate the ability of LLMs and agentic approaches to generate architecture views from source code. Method: We analyze 340 open-source repositories across 13 experimental configurations using 3 LLMs with 3 prompting techniques and 2 agentic approaches, yielding 4,137 generated views. We evaluate the generated views by comparing them with the ground-truth using a combination of automated metrics complemented by human evaluations. Results: Prompting strategies offer marginal improvements. Few-shot prompting reduces clarity failures by 9.2% compared to zero-shot baselines. The custom agentic approach consistently outperforms the general-purpose agent, achieving the best clarity (22.6% failure rate) and level-of-detail success (50%). Conclusions: LLM and agentic approaches demonstrate capabilities in generating syntactically valid architecture views. However, they consistently exhibit granularity mismatches, operating at the code level rather than architectural abstractions. This suggests that there is still a need for human expertise, positioning LLMs and agents as assistive tools rather than autonomous architects.