Agentic Artificial Intelligence in Software Quality Assurance: A Systematic Review of Methods and Impacts

Abstract

The increasing complexity of modern software systems has intensified the need for effective and efficient Software Quality Assurance (SQA) practices. Traditional SQA approaches often face limitations such as ambiguous requirements, incomplete test coverage, delayed defect detection, and a heavy reliance on manual testing. To address these challenges, recent research has explored the integration of Agentic Artificial Intelligence (AI), which is capable of autonomous decision-making, adaptive behavior, and goal-oriented reasoning. This study presents a systematic review of existing literature to examine how Agentic AI techniques are applied within SQA processes across the software development lifecycle. Using a structured review methodology, relevant peer-reviewed studies were analyzed to identify key application areas, including automated requirements clarification, intelligent test-case generation, predictive defect analysis, and continuous quality monitoring. The findings indicate that Agentic AI-based approaches contribute to improved early detection, reduced human error, enhanced testing efficiency, and increased adaptability to evolving project requirements when compared to traditional SQA methods. However, the review also highlights several challenges, such as model interpretability issues, data dependency, and integration complexity, which limit widespread adoption. Overall, this review demonstrates that Agentic AI has significant potential to enhance the effectiveness and reliability of SQA practices, while also identifying current limitations that must be addressed to enable broader practical implementation.