Artificial Intelligence in Software Testing: A Systematic Review of a Decade of Evolution and Taxonomy

Software testing is fundamental to ensuring the quality, reliability, and security of software systems. Over the past decade, artificial intelligence (AI) algorithms have been increasingly applied to automate testing processes, predict and detect defects, and optimize evaluation strategies. This systematic review examines studies published between 2014 and 2024, focusing on the taxonomy and evolution of algorithms across problems, variables, and metrics in software testing. A taxonomy of testing problems is proposed by categorizing issues identified in the literature and mapping the AI algorithms applied to them. In parallel, the review analyzes the input variables and evaluation metrics used by these algorithms, organizing them into established categories and exploring their evolution over time. The findings reveal three complementary trajectories: (1) the evolution of problem categories, from defect prediction toward automation, collaboration, and evaluation; (2) the evolution of input variables, highlighting the increasing importance of semantic, dynamic, and interface-driven data sources beyond structural metrics; and (3) the evolution of evaluation metrics, from classical performance indicators to advanced, testing-specific, and coverage-oriented measures. Finally, the study integrates these dimensions, showing how interdependencies among problems, variables, and metrics have shaped the maturity of AI in software testing. This review contributes a novel taxonomy of problems, a synthesis of variables and metrics, and a future research agenda emphasizing scalability, interpretability, and industrial adoption.