<p>Wire Arc Additive Manufacturing (WAAM) has emerged as a prominent metal additive manufacturing technology for producing large-scale components with high deposition rates. The integration of machine learning (ML) techniques with WAAM processes has gained significant attention in recent years, offering enhanced process control, defect detection, and parameter optimization capabilities. This comprehensive review examines the state-of-the-art applications of machine learning in WAAM, covering process monitoring, defect detection, and parameter optimization. The paper analyzes various ML algorithms including convolutional neural networks (CNNs), support vector machines (SVMs), random forests, and deep reinforcement learning applied to WAAM processes. Key findings reveal that ML-based approaches have achieved significant improvements in defect detection accuracy (up to 94.5% mean average precision), real-time process monitoring capabilities, and parameter optimization efficiency. The review also discusses the challenges associated with data collection, model generalization, and industrial implementation. Future research directions are identified, including the development of digital twins, integration with Industry 4.0 frameworks, and advanced spatiotemporal modeling techniques. This review provides valuable insights for researchers and practitioners working on intelligent manufacturing systems and highlights the potential of ML-driven WAAM technologies for next-generation manufacturing applications.</p> Graphical Abstract <p></p>