Ranapana, R. M. S.Wijayanayake, W. M. J. I.2025-09-102024Ranapana, R. M. S., & Wijayanayake, W. M. J. I. (2024). THE ROLE OF AI IN SOFTWARE TEST AUTOMATION - A SYSTEMATIC LITERATURE REVIEW (pp. 171–188). Desk Research Conference – DRC 2024, The Library, University of Kelaniya, Sri Lanka.http://repository.kln.ac.lk/handle/123456789/29899Artificial Intelligence (AI) has emerged as a transformative force in software test automation, enhancing the efficiency, accuracy, and reliability of testing processes. This systematic literature review investigates the role of AI in software test automation, focusing on key methodologies, applications, and challenges faced in its implementation. The review aims to identify and analyze the various AI-driven techniques such as Machine Learning (ML), Neural Networks, and Genetic Algorithms that are being utilized to optimize testing activities, including test case generation, defect detection, and test execution. The findings reveal that AI can significantly improve the software testing lifecycle by automating repetitive tasks, reducing human error, and increasing test coverage. By leveraging AI algorithms, organizations can achieve faster turnaround times and enhance the overall quality of software products. Moreover, AI facilitates predictive analytics, allowing teams to identify potential defects early in the development process, thus minimizing costs and time associated with late-stage bug fixes. However, the review also highlights several challenges that hinder the widespread adoption of AI in software testing. Issues such as data quality, model overfitting, and the complexity of integrating AI solutions with existing testing frameworks present significant barriers. Additionally, many AI applications remain largely theoretical or are limited to academic research, lacking real-world implementation. The insights gained from this review are invaluable for both researchers and practitioners seeking to harness the capabilities of AI to revolutionize software testing practices. By addressing the identified challenges and fostering collaboration between academia and industry, stakeholders can develop more robust frameworks and models that leverage AI's potential to create a more efficient and effective software testing environment.Artificial IntelligenceMachine LearningSoftware TestingTest AutomationEfficiencyArticle