The week's pick
Random Articles
Reseach Article
TestVerse: An AI-Powered Unified Platform for Automated Software Testing using Generative Models
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 105 |
| Year of Publication: 2026 |
| Authors: Abhijeet More, Manjusha Jambhale, Shubham Lonkar, Soham Bhatkhande, Prem Patil |
10.5120/ijcaec58112ccf72
|
Abhijeet More, Manjusha Jambhale, Shubham Lonkar, Soham Bhatkhande, Prem Patil . TestVerse: An AI-Powered Unified Platform for Automated Software Testing using Generative Models. International Journal of Computer Applications. 187, 105 ( May 2026), 27-37. DOI=10.5120/ijcaec58112ccf72
Abstract
Software testing is essential for developing reliable applications. Traditional testing tools often require significant maintenance, can be unreliable, and are primarily accessible to programmers. Recently, large-scale AI models have transformed the testing landscape by enabling more efficient and integrated automation approaches [2], [4].This paper presents TestVerse, an AI-powered testing platform that integrates both black-box and white-box testing in a unified framework. The system utilizes the Google Gemini API to enhance automation capabilities. It includes features such as an AI Script Generator that converts natural language testing objectives into Selenium scripts, a Natural Language Translator for step-by-step execution, and an AI Bug Assistant that identifies errors and suggests fixes. Additionally, the platform incorporates Visual Regression Testing for UI defect detection and a White-Box Analysis module that evaluates Python code, generates pytest-based unit tests, and improves code quality. The platform aims to reduce manual effort, minimize required expertise, improve defect detection accuracy, and integrate seamlessly with CI/CD workflows.
References
- D. Santiago, T. M. King, and P. J. Clarke, “AI-Driven Test Generation: Machines Learning from Human Testers,” 2017.
- S. A. Khan et al., “AI-Based Software Testing,” 2024.
- V. Garousi et al., “AI-powered software testing tools: A systematic review,” 2023.
- H. Agoro and A. Matthew, “AI-Powered Test Case Generation and Execution,” 2023.
- S. Nidhra and J. Dondeti, “Black box and white box testing techniques – A literature review,” 2012.
- J. Heinonen, “Design and Implementation of Automated Visual Regression Testing,” 2020.
- K. Karhu et al., “Expectations vs Reality: AI Adoption in Software Testing,” 2025.
- H. V. Pandhare, “From Test Case Design to Test Data Generation: AI Redefining QA,” 2024.
- S. I. Khaleel and R. Anan, “Optimal Test Cases for Regression Testing using AI Techniques,” 2023.
- M. A. Hayat et al., “The Evolving Role of AI in Software Testing: Prospects and Challenges,” 2024.
- S. Haroon, M. T. Khan, and M. A. Gulzar, “Evaluating LLM-Based Test Generation Under Software Evolution,” arXiv preprint, 2026.
- A. Lops et al., “A System for Automated Unit Test Generation Using Large Language Models and Assessment of Generated Test Suites,” IEEE ICST Workshops (ICSTW), 2025.
- W. Xu, M. Liu, and F. Kong, “Enhancing LLM-Based Test Generation by Eliminating Covered Code,” arXiv preprint, 2026.
- A. S. Yaraghi et al., “Scalable and Accurate Test Case Prioritization in Continuous Integration Contexts,” IEEE Trans. Software Eng., vol. 49, no. 4, pp. 1615–1639, 2023
Index Terms
Keywords