PortAgent: LLM-driven Vehicle Dispatching Agent for Port Terminals

TL;DR

This paper introduces PortAgent, an LLM-based vehicle dispatching system that automates port terminal operations transfer, reducing reliance on specialists, data needs, and deployment time, thus improving efficiency and transferability.

Contribution

PortAgent is the first LLM-driven VDS that fully automates transfer workflows, eliminating specialist dependency and enabling rapid, low-data deployment across diverse port terminals.

Findings

Achieves no need for port operation specialists.

Requires minimal terminal-specific data.

Enables fast deployment across different terminals.

Abstract

Vehicle Dispatching Systems (VDSs) are critical to the operational efficiency of Automated Container Terminals (ACTs). However, their widespread commercialization is hindered due to their low transferability across diverse terminals. This transferability challenge stems from three limitations: high reliance on port operational specialists, a high demand for terminal-specific data, and time-consuming manual deployment processes. Leveraging the emergence of Large Language Models (LLMs), this paper proposes PortAgent, an LLM-driven vehicle dispatching agent that fully automates the VDS transferring workflow. It bears three features: (1) no need for port operations specialists; (2) low need of data; and (3) fast deployment. Specifically, specialist dependency is eliminated by the Virtual Expert Team (VET). The VET collaborates with four virtual experts, including a Knowledge Retriever, Modeler, Coder, and Debugger, to emulate a human expert team for the VDS transferring workflow. These experts specialize in the domain of terminal VDS via a few-shot example learning approach. Through this approach, the experts are able to learn VDS-domain knowledge from a few VDS examples. These examples are retrieved via a Retrieval-Augmented Generation (RAG) mechanism, mitigating the high demand for terminal-specific data. Furthermore, an automatic VDS design workflow is established among these experts to avoid extra manual interventions. In this workflow, a self-correction loop inspired by the LLM Reflexion framework is created