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

descriptionPublicationkeyboard_double_arrow_right Article , Conference object , Preprint 01 Jun 2026Embargo end date: 01 Mar 2026Publisher:IEEEJournal:2026 IEEE 23rd International Conference on Software Architecture (ICSA)

Authors: Vaidhyanathan, Karthik; Dhar, Rudra; Miryala, Sathvika;

doi: 10.1109/icsa66085.2026.00031 , 10.5281/zenodo.18772572 , 10.48550/arxiv.2603.21178 , 10.5281/zenodo.18772573

arXiv: 2603.21178

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

- Summary
- Subjects
- Metrics

Abstract

This repository contains the complete experimental data and source code for the study on "LLM-based Automated Architecture View Generation: Where Are We Now?" The project explores automated knowledge extraction from software repositories and the subsequent generation of structured architectural diagrams using Large Language Models.The study evaluates multiple prompting strategies against a ground truth dataset of hundreds of open-source projects to generate Architectural Views.

Keywords

Software Engineering (cs.SE), FOS: Computer and information sciences, Artificial Intelligence (cs.AI), Artificial Intelligence, Software Engineering

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average

Found an issue? Give us feedback

0

Average