Virtual Traffic Police: Large Language Model-Augmented Traffic Signal Control for Unforeseen Incidents

2026-01-22

AI Summary

This study addresses the limitations of traditional adaptive traffic signal control systems, which exhibit delayed responses to unexpected traffic incidents—such as accidents or roadwork—and often rely on inefficient manual interventions. To overcome this, the authors propose a hierarchical framework that employs a large language model (LLM) as a virtual traffic officer to dynamically fine-tune the parameters of existing lower-level signal controllers in real time. The approach innovatively integrates retrieval-augmented generation (RAG), a domain-specific traffic language database, and an LLM validation mechanism to construct a self-optimizing traffic-language retrieval system. This enhances the adaptability and reliability of conventional control algorithms without replacing them. Experimental results demonstrate that the proposed method significantly improves operational efficiency during突发 scenarios, confirming the LLM’s viability as a trustworthy virtual traffic officer.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Learning to Search
• Multiagent Systems: Agent Communication

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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, whereby a virtual traffic police agent at the upper level dynamically fine-tunes selected parameters of signal controllers at the lower level in response to real-time traffic incidents. To enhance domain-specific reliability in response to unforeseen traffic incidents, we devise a self-refined traffic language retrieval system (TLRS), whereby retrieval-augmented generation is employed to draw knowledge from a tailored traffic language database that encompasses traffic conditions and controller operation principles. Moreover, we devise an LLM-based verifier to update the TLRS continuously over the reasoning process. Our results show that LLMs can serve as trustworthy virtual traffic police officers that can adapt conventional TSC methods to unforeseen traffic incidents with significantly improved operational efficiency and reliability.

Problem

• traffic signal control
• unforeseen incidents
• manual intervention
• adaptive traffic management
• traffic accidents

Innovation

• Large Language Model
• Traffic Signal Control
• Retrieval-Augmented Generation
• Hierarchical Framework
• Unforeseen Incidents