Abstract: High-throughput screening (HTS) has been widely used in drug discovery recently. It allows batch bioactivity testing of compounds, thereby accelerating the identification of bioactive molecules. However, its screening efficiency and accuracy remain limited. Therefore, artificial intelligence (AI) is gradually integrated into the process of HTS, such as machine learning and deep learning algorithms to enhance ligand-based virtual screening, drug combination screening, and analysis of images, to promote the intelligent development of drug discovery. This review summarized the recent advances in the application of AI technologies in HTS, discussed the applications of machine learning models, and highlighted key AI applications in compound screening and recognition of image in HTS to accelerate the development of innovative drugs.