PortAgent: LLM-driven Vehicle Dispatching Agent for Port Terminals

By: Jia Hu, Junqi Li, Weimeng Lin, Peng Jia, Yuxiong Ji, Jintao Lai

Published: 2025-12-17

View on arXiv →
#cs.AI

Abstract

This paper introduces PortAgent, an LLM-driven vehicle dispatching agent designed to fully automate the Vehicle Dispatching System (VDS) transferring workflow in Automated Container Terminals (ACTs). PortAgent addresses issues of low transferability, high reliance on specialists, and extensive data demands by employing a Virtual Expert Team (VET) and a self-correction loop, achieving high success rates and rapid deployment.

FEEDBACK

Projects

No projects yet

PortAgent: LLM-driven Vehicle Dispatching Agent for Port Terminals | ArXiv Intelligence