Potentials of generative AI in logistics and supply chain management: a guiding review on applications and future research directions

Abstract

Generative artificial intelligence (GenAI) is emerging as a transformative technology in logistics and supply chain management (LSCM), offering functions that extend beyond traditional AI methods by enabling synthetic data generation, scenario simulation, and decision support. This study presents a comprehensive systematic literature review of 43 peer-reviewed papers that investigate the application of GenAI across diverse LSCM functions. The review synthesises current knowledge on how GenAI technologies, such as generative adversarial networks (GANs), variational autoencoders (VAEs), or transformers are being applied in forecasting, inventory control, warehouse management, risk management/assessment, and other supply chain domains. To structure the analysis, we develop a conceptual framework that maps specific GenAI technologies and their underlying capabilities to specific LSCM application areas. The findings reveal a strong focus on operational optimisation, particularly in forecasting and inventory control, while areas such as sustainable supply chain management, transportation, and supply chain automation remain underexplored. Moreover, the majority of studies in our sample rely on simulation approaches and use artificial datasets based on predictive modelling, while empirical field studies remain notably scarce. This review contributes by consolidating fragmented research, identifying promising avenues for future studies, and highlighting the potential of GenAI to enhance digital transformation and innovation in LSCM.