Thermal energy storage (TES) plays a pivotal role in a wide array of energy systems, offering a highly effective means to harness renewable energy sources, trim energy consumption and costs, reduce environmental impact, and bolster the adaptability and dependability of power grids. Concurrently, artificial intelligence (AI) has risen in prominence for optimizing and fine-tuning TES systems. Various AI techniques, such as particle swarm optimization, artificial neural networks, support vector machines, and adaptive neuro-fuzzy inference systems, have been extensively explored in the realm of energy storage. This study provides a comprehensive overview of how AI, across diverse applications, categorizes, and optimizes energy systems. The study critically evaluates the effectiveness of these AI technologies, highlighting their impressive accuracy in achieving a range of objectives. Through a thorough analysis, the paper also offers valuable recommendations and outlines future research directions, aiming to inspire innovative concepts and advancements in leveraging AI for TESS. By bridging the gap between TES and AI techniques, this study contributes significantly to the progress of energy systems, enhancing their efficiency, reliability, and sustainability. The insights gleaned from this research will be invaluable for researchers, engineers, and policymakers, aiding them in making well-informed decisions regarding the design, operation, and management of energy systems integrated with TES.