Abstract

Software testing plays a crucial role in ensuring the reliability and quality of modern applications, but traditional automation methods often struggle with scalability, maintenance, and efficiency. This research proposes an AI-Augmented Test Automation Framework that integrates the Page Object Model (POM) and Behavior-Driven Development (BDD) to enhance intelligent and scalable software testing. The framework leverages AI-driven test case generation, prioritization, and self-healing mechanisms using reinforcement learning to optimize execution time, defect detection, and maintenance costs. Performance evaluation, conducted using the Bugzilla Bug Reports Dataset, demonstrates that the proposed method outperforms conventional test automation techniques, achieving higher defect detection rates (91%), reduced execution time (95s), and improved test coverage efficiency (94%). Comparative analysis against traditional methods such as NOMA, UVFA, and DGNN further highlights its superiority in resource allocation, adaptability, and error reduction. The results validate the proposed approach as a robust and scalable solution for enhancing automated software testing.