Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Ranah Research : Journal of Multidisciplinary Research and Development
Ditasari, Linmas
Unknown Affiliation
Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Economics, Econometrics & Finance Law, Crime, Criminology & Criminal Justice Public Health Social Sciences Transportation Other

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Generative AI-Based Software Testing Implementation Model in Agile Development Methodology: Systematic Literature Review Ditasari, Linmas; Raharjo, Teguh
Ranah Research : Journal of Multidisciplinary Research and Development Vol. 8 No. 3 (2026): Ranah Research : Journal Of Multidisciplinary Research and Development
Publisher : Dinasti Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38035/rrj.v8i3.2056

Abstract

The development of Artificial Intelligence (AI) technology, particularly Generative AI and Large Language Models (LLM), has had a significant impact on the software development process, including software testing activities. This study aims to conduct a Systematic Literature Review (SLR) to identify and analyze various Generative AI-based software testing frameworks applied in Agile development environments. The literature search process was conducted in several major scientific databases, namely IEEE Xplore, Scopus, ScienceDirect, SpringerLink, and Google Scholar with a publication period of 2021–2026. Based on the selection process using the PRISMA method, 35 articles were obtained that met the inclusion criteria. The analysis results show that most studies utilize Large Language Models (LLM), machine learning, generative models, and retrieval-augmented generation (RAG) techniques to support software test automation, such as test case generation, unit testing automation, and behavior-driven development testing. In addition, several studies also developed AI assistant and agentic AI-based frameworks that can be integrated into Agile development pipelines. This study found that the use of Generative AI can improve testing process efficiency, accelerate test case generation, and help improve software quality. However, several challenges remain, such as limited model accuracy, the need for high-quality datasets, and issues with the security and reliability of AI-based systems
Co-Authors Raharjo, Teguh