Generative AI for software architecture. Applications, challenges, and future directions

IF 4.1 2区计算机科学 Q1 COMPUTER SCIENCE, SOFTWARE ENGINEERING

Journal of Systems and Software Pub Date : 2025-09-17 DOI:10.1016/j.jss.2025.112607

Matteo Esposito , Xiaozhou Li , Sergio Moreschini , Noman Ahmad , Tomas Cerny , Karthik Vaidhyanathan , Valentina Lenarduzzi , Davide Taibi

{"title":"Generative AI for software architecture. Applications, challenges, and future directions","authors":"Matteo Esposito , Xiaozhou Li , Sergio Moreschini , Noman Ahmad , Tomas Cerny , Karthik Vaidhyanathan , Valentina Lenarduzzi , Davide Taibi","doi":"10.1016/j.jss.2025.112607","DOIUrl":null,"url":null,"abstract":"<div><h3>Context:</h3><div>Generative Artificial Intelligence (GenAI) is transforming much of software development, yet its application in software architecture is still in its infancy.</div></div><div><h3>Aim:</h3><div>Systematically synthesize the use, rationale, contexts, usability, and challenges of GenAI in software architecture.</div></div><div><h3>Method:</h3><div>Multivocal literature review (MLR), analyzing peer-reviewed and gray literature, identifying current practices, models, adoption contexts, reported challenges, and extracting themes via open coding.</div></div><div><h3>Results:</h3><div>This review identifies a significant adoption of GenAI for architectural decision support and architectural reconstruction. OpenAI GPT models are predominantly applied, and there is consistent use of techniques such as few-shot prompting and retrieval-augmented generation (RAG). GenAI has been applied mostly to the initial stages of the Software Architecture Life Cycle (SALC), such as Requirements-to-Architecture and Architecture-to-Code. Monolithic and microservice architectures were the main targets. However, rigorous testing of GenAI outputs was typically missing from the studies. Among the most frequent challenges are model precision, hallucinations, ethical aspects, privacy issues, lack of architecture-specific datasets, and the absence of sound evaluation frameworks.</div></div><div><h3>Conclusions:</h3><div>GenAI shows significant potential in software design, but there are several challenges on its way towards greater adoption. Research efforts should target designing general evaluation methodologies, handling ethics and precision, increasing transparency and explainability, and promoting architecture-specific datasets and benchmarks to overcome the gap between theoretical possibility and practical use.</div><div><em>Editor’s note: Open Science material was validated by the Journal of Systems and Software Open Science Board</em>.</div></div>","PeriodicalId":51099,"journal":{"name":"Journal of Systems and Software","volume":"231 ","pages":"Article 112607"},"PeriodicalIF":4.1000,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Systems and Software","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0164121225002766","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}

引用次数: 0

Abstract

Context:

Generative Artificial Intelligence (GenAI) is transforming much of software development, yet its application in software architecture is still in its infancy.

Aim:

Systematically synthesize the use, rationale, contexts, usability, and challenges of GenAI in software architecture.

Method:

Multivocal literature review (MLR), analyzing peer-reviewed and gray literature, identifying current practices, models, adoption contexts, reported challenges, and extracting themes via open coding.

Results:

This review identifies a significant adoption of GenAI for architectural decision support and architectural reconstruction. OpenAI GPT models are predominantly applied, and there is consistent use of techniques such as few-shot prompting and retrieval-augmented generation (RAG). GenAI has been applied mostly to the initial stages of the Software Architecture Life Cycle (SALC), such as Requirements-to-Architecture and Architecture-to-Code. Monolithic and microservice architectures were the main targets. However, rigorous testing of GenAI outputs was typically missing from the studies. Among the most frequent challenges are model precision, hallucinations, ethical aspects, privacy issues, lack of architecture-specific datasets, and the absence of sound evaluation frameworks.

Conclusions:

GenAI shows significant potential in software design, but there are several challenges on its way towards greater adoption. Research efforts should target designing general evaluation methodologies, handling ethics and precision, increasing transparency and explainability, and promoting architecture-specific datasets and benchmarks to overcome the gap between theoretical possibility and practical use.

Editor’s note: Open Science material was validated by the Journal of Systems and Software Open Science Board.

查看原文本刊更多论文

软件架构的生成式AI。应用、挑战和未来方向

背景：生成式人工智能（GenAI）正在改变许多软件开发，但它在软件架构中的应用仍处于起步阶段。目的：系统地综合GenAI在软件架构中的使用、基本原理、上下文、可用性和挑战。方法：多声音文献综述（MLR），分析同行评审和灰色文献，识别当前的实践、模型、采用背景、报告的挑战，并通过开放编码提取主题。结果：这篇综述确定了GenAI在架构决策支持和架构重建方面的重要应用。OpenAI GPT模型的应用占主导地位，并且一直使用少量提示和检索增强生成（RAG）等技术。GenAI主要应用于软件体系结构生命周期（SALC）的初始阶段，例如需求到体系结构和体系结构到代码。单片和微服务架构是主要目标。然而，这些研究通常缺少对GenAI产出的严格测试。其中最常见的挑战是模型精度、幻觉、伦理方面、隐私问题、缺乏特定于体系结构的数据集以及缺乏健全的评估框架。结论：GenAI在软件设计中显示了巨大的潜力，但是在它被广泛采用的道路上还有一些挑战。研究工作的目标应该是设计一般的评估方法，处理伦理和准确性，增加透明度和可解释性，促进特定于体系结构的数据集和基准，以克服理论可能性和实际应用之间的差距。编者注：开放科学材料由系统与软件开放科学委员会杂志验证。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Systems and Software 工程技术-计算机：理论方法

CiteScore

8.60

自引率

5.70%

发文量

193

审稿时长

16 weeks

期刊介绍： The Journal of Systems and Software publishes papers covering all aspects of software engineering and related hardware-software-systems issues. All articles should include a validation of the idea presented, e.g. through case studies, experiments, or systematic comparisons with other approaches already in practice. Topics of interest include, but are not limited to: •Methods and tools for, and empirical studies on, software requirements, design, architecture, verification and validation, maintenance and evolution •Agile, model-driven, service-oriented, open source and global software development •Approaches for mobile, multiprocessing, real-time, distributed, cloud-based, dependable and virtualized systems •Human factors and management concerns of software development •Data management and big data issues of software systems •Metrics and evaluation, data mining of software development resources •Business and economic aspects of software development processes The journal welcomes state-of-the-art surveys and reports of practical experience for all of these topics.