Abstract:Binocular vision dysfunction (BVD) encompasses a range of conditions affecting ocular alignment, vergence, accommodation, and sensory fusion, yet conventional assessment methods remain limited by subjectivity, examiner variability and poor reproducibility. Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), has emerged as a promising adjunct in the objective assessment and diagnosis of BVD. This narrative review synthesizes current evidence on AI applications across eye tracking and oculomotor analysis, automated ocular alignment detection, vergence and accommodative measurement, stereoacuity assessment, and diagnosis of convergence insufficiency, strabismus, amblyopia, and nystagmus. AI-driven tools demonstrate strong diagnostic performance, with several systems achieving sensitivity and specificity exceeding 90%. Smartphone-based and wearable platforms further extend BVD care to remote and resource-limited settings. However, limitations including small training datasets, lack of external validation, inconsistent diagnostic criteria, and limited model interpretability must be addressed before routine clinical integration. AI currently functions best as a decision-support tool rather than a replacement for expert clinical assessment.