Accurate diagnosis of lymph node metastasis is critical for cancer staging, treatment selection, and prognostic evaluation. Computed tomography（CT）, as a conventional imaging modality, plays a significant role in diagnosing lymph node metastasis. However, it remains limited in the identification of nodes with short-axis diameter ＜1 cm and micrometastases. In recent years, artificial intelligence（AI） technology has advanced rapidly in the field of medical image analysis, offering novel technical pathways to improve the accuracy of CT-based diagnosis of lymph node metastasis. This article reviews the research progress in AI-assisted CT diagnosis of lymph node metastasis, with a focus on the technical characteristics, diagnostic performance, and clinical applications of radiomics, deep learning, and their integrated models across various cancer types. Future directions and existing challenges are also discussed.