ITSC 2025 Paper Abstract

Paper TH-LA-T23.3

Wang, Qiqing (National University of Singapore), Wei, Shiqi (National University of Singapore), Yang, Kaidi (National University of Singapore)

LLMs As Virtual Traffic Police: Incident-Aware Traffic Signal Control Augmented by Large Language Models

Scheduled for presentation during the Invited Session "S23c-Trustworthy AI for Traffic Sensing and Control" (TH-LA-T23), Thursday, November 20, 2025, 16:40−17:00, Coolangata 2

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Keywords AI, Machine Learning for Dynamic Traffic Signal Control and Optimization, AI, Machine Learning and Predictive Analytics for Traffic Incident Detection and Management

Abstract

Adaptive traffic signal control (TSC) has demonstrated strong effectiveness in managing dynamic traffic flows. However, conventional methods often struggle when unforeseen traffic incidents occur (e.g., accidents and road maintenance), which typically require labor-intensive and inefficient manual interventions by traffic police officers. Large Language Models (LLMs) appear to be a promising solution thanks to their remarkable reasoning and generalization capabilities. Nevertheless, existing works often propose to replace existing TSC systems with LLM-based systems, which can be (i) unreliable due to the inherent hallucinations of LLMs and (ii) costly due to the need for system replacement. To address the issues of existing works, we propose a hierarchical framework that augments existing TSC systems with LLMs. This framework leverages LLMs at the upper level to dynamically fine-tune selected parameters of signal controllers at the lower level in response to real-time traffic incidents. To enhance domain-specific reliability, we employ Retrieval-Augmented Generation (RAG) to draw knowledge from a tailored traffic language database that encompasses traffic conditions and controller operation principles. Our results show that LLMs can serve as trustworthy virtual traffic police officers that can adapt conventional TSC methods to traffic incidents with significantly improved operational efficiency and reliability.