Leveraging Generative AI for Test Case Creation in Complex Systems

Year : 2025 | Volume : 12 | Issue : 03 | Page : 16 22
    By

    Sachin Shankarrao Ajmire,

  • Karuna Vivekanand Agarkar,

  1. Research Scholar, Department of MCA (Master of Computer Application), G H Raisoni University, Amravati, Maharashtra, India
  2. Research Scholar, Department of Bachelor of Commerce, G H Raisoni University, Amravati, Maharashtra, India

Abstract

Modern software systems exhibit increasing complexity, demanding sophisticated testing methodologies to ensure reliability and functionality. Traditional manual testing approaches often struggle to keep pace with this complexity, leading to inadequate test coverage and increased risk of unforeseen issues. This study explores the potential of Generative AI (GAI) in revolutionizing test case creation for complex systems. We delve into the practical application of GAI techniques, such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs), to generate diverse and realistic test inputs, simulate user behavior, and identify critical edge cases. We discuss the benefits of GAI-driven testing, including enhanced test coverage, improved fault detection, and accelerated testing cycles. Furthermore, we address the inherent challenges, such as data quality requirements, model interpretability, and the need for robust evaluation metrics. Finally, we present a roadmap for successful GAI implementation in real-world testing scenarios, emphasizing the importance of human-in-the-loop approaches and continuous model refinement.

Keywords: Generative AI, test data, complex systems, software testing, generative adversarial networks (GAN), variable autoencoders (VAE), transformers, model training, data collection, program extension, efficiency, adaptability, verification, integration, edge cases, error detection, user reporting, system logging, workflow evaluation, hybrid model, automatic verification

[This article belongs to Recent Trends in Programming languages ]

How to cite this article:
Sachin Shankarrao Ajmire, Karuna Vivekanand Agarkar. Leveraging Generative AI for Test Case Creation in Complex Systems. Recent Trends in Programming languages. 2025; 12(03):16-22.
How to cite this URL:
Sachin Shankarrao Ajmire, Karuna Vivekanand Agarkar. Leveraging Generative AI for Test Case Creation in Complex Systems. Recent Trends in Programming languages. 2025; 12(03):16-22. Available from: https://journals.stmjournals.com/rtpl/article=2025/view=232666


References

  1. Ale NK. Implementing Machine Learning Algorithms to Improve Test Case Generation and Execution. Journal of Scientific and Engineering Research. 2022; 9(7): 151–7.
  2. Guo X, Okamura H, Dohi T. Automated software test data generation with generative adversarial networks. IEEE Access. 2022 Feb 22; 10: 20690–700.
  3. Talakola S. The optimization of software testing efficiency and effectiveness using AI techniques. International Journal of Artificial Intelligence, Data Science, and Machine Learning. 2024 Oct 31; 5(3): 23–34.
  4. Bajaj Y, Samal MK. Accelerating software quality: Unleashing the power of generative ai for automated test-case generation and bug identification. Int J Res Appl Sci Eng Technol. 2023 Jul; 11(7): 345–50.
  5. Korol V. Integrating AI Tools Into the Continuous Testing Process. The American Journal of Engineering and Technology (TAJET). 2025 Jun 30; 7(06): 222–9.
  6. Natarajan DR. AI-Generated Test Automation for Autonomous Software Verification: Enhancing Quality Assurance Through AI-Driven Testing. International Journal of HRM and Organizational Behavior. 2020 Nov 18; 8(4): 89–103.
  7. Othman R, Zein S. Test Case Auto-Generation For Web Applications: A Model-Based Approach. In 2022 IEEE International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT). 2022 Oct 20; 18–25.
  8. Mohapatra PS. Artificial Intelligence-Driven Test Case Generation in Software Development. In: Intelligent Assurance: Artificial Intelligence-Powered Software Testing in the Modern Development Lifecycle. Deep Science Publishing; Turkey. 2025 Jul 27; 4: 1-163.
  9. Bajaj Y, Samal MK. Accelerating software quality: Unleashing the power of generative ai for automated test-case generation and bug identification. Int J Res Appl Sci Eng Technol. 2023 Jul; 11(7): 345–50.
  10. Plein L, Ouédraogo WC, Klein J, Bissyandé TF. Automatic generation of test cases based on bug reports: a feasibility study with large language models. In Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings. 2024 Apr 14; 360–361.
  11. Nabeel M, Nimara DD, Zanouda T. Test code generation for telecom software systems using two-stage generative model. In 2024 IEEE International Conference on Communications Workshops (ICC Workshops). 2024 Jun 9; 1231–1236.
  12. Baqar M, Khanda R. The Future of Software Testing: AI–Powered Test Case Generation and Validation. In Intelligent Computing-Proceedings of the Computing Conference. Cham: Springer Nature Switzerland; 2025 Jun 19; 276–300.
  13. Porres I, Rexha H, Lafond S. Online GANs for automatic performance testing. In 2021 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). 2021 Apr 12; 95–100.
  14. Damyanov I, Tsankov N, Nedyalkov I. Applications of Generative Artificial Intelligence in the Software Industry. TEM J. 2024 Nov 1; 13(4): 2724–2733.
  15. Bandi A, Nukala HS, Tatavarthi B, Boggavarapu A. Automated Test Case Generation for Software Testing Using Generative AI. In International Conference on Computers and Their Applications. Cham: Springer Nature Switzerland; 2025 Mar 17; 78–87.
  16. Sun L, Tao S, Hu J, Dow SP. Metawriter: Exploring the potential and perils of ai writing support in scientific peer review. Proc ACM Hum-Comput Interact. 2024 Apr 23; 8(CSCW1): 1–32.
  17. Muhammad A. AI-Driven Testing Automation: Harnessing Machine Learning for Intelligent Test Case Creation and Predictive Defect Analysis. Int J Artif Intell Appl. 2024; 9(3): 22–35.
  18. Hernández R, Manuel B, Ayala S, Martın J, Melo M, Andrés J. Generative ai for software architecture. Tech rep. Fundación Universitaria de Ciencias de la Salud; 2024 Jun 3.
  19. Mehralian M, Karasfi B. RDCGAN: Unsupervised representation learning with regularized deep convolutional generative adversarial networks. In 2018 IEEE 9th conference on artificial intelligence and robotics and 2nd Asia-pacific international symposium. 2018 Dec 10; 31–38.
  20. Rybkin O, Daniilidis K, Levine S. Simple and effective VAE training with calibrated decoders. In International conference on machine learning, PMLR. 2021 Jul 1; 9179–9189.
  21. Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S. Language models are few-shot learners. Adv Neural Inf Process Syst. 2020; 33: 1877–901.
  22. Reed S, Akata Z, Yan X, Logeswaran L, Schiele B, Lee H. Generative adversarial text to image synthesis. In International conference on machine learning, PMLR. 2016 Jun 11; 1060–1069.
  23. Brock A, Donahue J, Simonyan K. Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096. 2018 Sep 28.
Regular Issue Subscription Original Research
Volume 12
Issue 03
Received 12/05/2025
Accepted 05/06/2025
Published 17/10/2025
Publication Time 158 Days
108

Login


My IP

PlumX Metrics