The rapid rise of consumption-driven markets has intensified challenges within reverse supply chain logistics (RSCL), particularly in the Fast-Moving Consumer Goods (FMCG) sector, where product returns, waste management, recycling, and environmental compliance require efficient handling. This paper provides a comprehensive review of how Artificial Intelligence (AI) enhances decision-making across reverse supply chain logistics processes, including return forecasting, defect diagnosis, route optimisation, waste reduction, and circular economy integration. The study synthesises literature from recent industry developments, case studies, and academic findings to identify key AI applications such as machine learning-based demand prediction, automated sorting using computer vision, blockchain-enabled tracking, and real-time optimisation through IoT sensors. The review highlights that AI-driven reverse supply chain logistics not only reduces operational costs but also supports sustainability goals and corporate social responsibility initiatives. However, challenges such as technological integration costs, data privacy, skill gaps, and infrastructure limitations remain. The paper concludes by outlining future research directions, emphasising automation maturity, multi-agent AI systems, and hybrid optimisation models. This paper therefore aims to: (a) map current AI applications in RSCL relevant to FMCG (forecasting, vision-based sorting, routing, traceability, and decision optimization); (b) evaluate national (Indian) and international examples and lessons learned from corporate pilots and programs; and (c) identify remaining technological, organizational, and policy barriers and propose directions for research and practice that enable scalable, equitable, and sustainable AI-enabled reverse logistics