Purpose: The integration of AI &ML technologies revolutionized last-mile delivery optimization in retort to the exponential growth in the global e-commerce market. Efficient last-mile logistics have become crucial to meeting consumer demands and operational challenges in the transport industry. Methodology: This study adopted a systematic literature review (SLR) united with a bibliometric analysis approach to explore and analyze existing literature on AI & ML applications in last-mile delivery optimization. By employing targeted keywords - “last mile,” “machine learning,” and “artificial intelligence” a comprehensive review of academic articles and review papers is conducted. A total of 81 research articles are screened and analyzed using bibliometric techniques, including co-occurrence analysis and co-citation author analysis, to identify key themes and trends. Findings: The analysis has revealed significant thematic clusters, highlighting spreads in last-mile delivery strategies, digital transformation and the influence of pandemic situations on logistics operations. Co-authorship analysis has unveiled collaborative networks among researchers, emphasizing the contributions of influential authors to the field. The study has also tracked the chronological evolution of publication trends, providing insights into emerging research directions. By identifying critical gaps and emerging research directions, this research has paved the way for advancements in logistics and transportation systems. The research proposes solutions for last-mile delivery challenges by employing quantitative techniques using AI/ML tools. Four critical gaps are investigated, including comparative studies on vehicle capacity optimization, machine learning approaches for dynamic routing, and AI-based systems for enhancing first-time delivery success rates in the last-mile.