AI-powered test automation tools: A systematic review and empirical evaluation (2409.00411v1)

Abstract: Context: Test engineers are looking at more ways to test systems more effectively and efficiently. With recent advances in the field of AI (Artificial Intelligence), a large number of AI-powered test automation tools have emerged, which can help make testing more effective and efficient. Objective: We investigate the features provided by existing AI-based test automation tools. We also empirically evaluate the performance of two AI-based testing tools by applying them on two selected open-source Software Under Test (SUT). We empirically evaluate how the AI features can be helpful for effectiveness and efficiency of testing. We also study the limitations of the AI features in AI-based test tools. Method: To accomplish the objective, a Multivocal Literature Review (MLR) study was conducted to investigate the landscape of the AI-based test automation tools in the industry. Moreover, an empirical assessment is also conducted to empirically analyze two AI-based test automation tools by using it on two open-source projects. To determine the need of AI for selected feature, the same feature was created without the use of ML to explore its limitations which can be avoided using AI. Results: Our results are based on 55 AI-based test automation tools. Furthermore, an empirical assessment was performed by selecting two of the 55 tools analyzed as part of the MLR. Conclusion: This paper explores the potential benefits and limitations of AI-based test automation tools. The limitations explored can be used as inspiration to develop better AI-based test tools.