AI-POWERED AUTONOMOUS FREIGHT DISPATCHING SYSTEM USING LARGE LANGUAGE MODELS AND MULTI-AGENT ARCHITECTURE

Authors

  • Sardorbek Sherdullaev Author

Keywords:

Artificial Intelligence, Large Language Models, Freight Dispatching, Multi-Agent Systems, Autonomous Logistics, Retrieval-Augmented Generation (RAG), Transportation Management Systems, Intelligent Decision Support.

Abstract

The rapid digital transformation of the freight transportation industry has accelerated the adoption of Artificial Intelligence (AI) to improve operational efficiency, reduce transportation costs, and support real-time decision-making. Despite significant advances in Transportation Management Systems (TMS), freight dispatching remains highly dependent on human dispatchers who manually search for loads, negotiate with brokers, communicate with drivers, and monitor shipment execution. These labor-intensive processes often result in delayed decisions, inconsistent load selection, and limited operational scalability.

This study proposes an AI-powered autonomous freight dispatching framework based on Large Language Models (LLMs) integrated with a multi-agent architecture. The proposed system decomposes dispatching tasks into specialized intelligent agents responsible for freight discovery, broker negotiation, route evaluation, document processing, risk assessment, and driver communication. To enhance factual reliability and minimize hallucinations, the architecture incorporates a Retrieval-Augmented Generation (RAG) module that retrieves relevant information from logistics databases, brokerage policies, carrier agreements, and transportation documents before generating responses.

Unlike conventional dispatching software that primarily performs data management, the proposed framework enables autonomous reasoning, contextual decision-making, and natural-language interaction across logistics workflows. The architecture is designed to integrate seamlessly with existing Transportation Management Systems and freight marketplaces while supporting scalable automation in dynamic logistics environments.

The paper presents the conceptual system architecture, workflow design, agent collaboration mechanisms, and evaluation framework for measuring operational performance. The proposed approach aims to reduce dispatcher workload, improve freight matching accuracy, accelerate broker communication, and increase overall operational efficiency. The findings contribute to the growing body of research on intelligent logistics systems by demonstrating how Large Language Models and collaborative AI agents can transform freight dispatching into a highly autonomous decision-support process suitable for next-generation digital logistics platforms.

References

1.Toth, P., & Vigo, D. (2014). Vehicle Routing: Problems, Methods, and Applications. SIAM, Philadelphia.

2.Guo, T., Chen, X., Wang, Y., et al. (2024). “Large Language Model Based Multi-agents: A Survey of Progress and Challenges,” Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024). DOI: 10.24963/ijcai.2024/890.

3.Li, X., Wang, S., Zeng, S., et al. (2024). “A Survey on LLM-based Multi-Agent Systems: Workflow, Infrastructure, and Challenges,” Springer Nature (Vicinagearth / related survey publications on LLM agents).

4.Fan, W., Ding, Y., Ning, L., et al. (2024). “A Survey on Retrieval-Augmented Generation for Large Language Models,” arXiv preprint arXiv:2405.06211.

5.Lewis, P., Perez, E., Piktus, A., et al. (2020). “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” Advances in Neural Information Processing Systems (NeurIPS 2020).

6.Sutton, R. S., & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press.

7.Russell, S., & Norvig, P. (2021). Artificial Intelligence: A Modern Approach (4th ed.). Pearson.

8.Davidsson, P., Henesey, L., Ramstedt, L., Törnquist, J., & Wernstedt, F. (2005). “An Analysis of Agent-Based Approaches to Transport Logistics,” Transportation Research Part C: Emerging Technologies, 13(4), 255–271.

Downloads

Published

2026-07-08