AI agents for decision support in logistics management: a literature review

Abstract

The increasing complexity, volatility, and sustainability pressures affecting global supply chains have accelerated the adoption of Artificial Intelligence (AI) technologies in logistics management. Among these AI approaches, Intelligent Agents (IAs) and Multi-agent Systems (MAS) have emerged as essential tools for supporting decentralized, adaptive, event-driven, and real-time decision-making processes in dynamic logistics environments. Unlike traditional centralized planning systems, agent-based approaches enable autonomous entities such as suppliers, warehouses, transportation units, and distribution centers to coordinate actions, exchange information, and manage variability. This paper presents a structured literature review of peer-reviewed studies indexed in Scopus and Web of Science on the use of AI agents to support decision-making in logistics management and supply chain operations. Particular attention is given to the strategic importance of intelligent agents in strengthening resilience, operational efficiency, and sustainability in increasingly uncertain logistics systems. The findings indicate that intelligent agents improve decision quality, responsiveness, coordination, and resource utilization across distributed logistics networks. Furthermore, Multi-Agent Systems enhance interoperability and collaboration among logistics actors, enabling more agile and resilient supply chains. However, challenges related to data quality, cybersecurity, governance, scalability, and human–AI collaboration continue to limit large-scale implementation in industrial environments.