Retrieval Augmented Generation-Enhanced Distributed LLM Agents for Generalizable Traffic Signal Control with Emergency Vehicles

TL;DR

This paper introduces a Retrieval Augmented Generation-enhanced distributed LLM agent framework for generalizable traffic signal control, especially effective during emergencies, improving traffic flow and emergency vehicle response across diverse intersections.

Contribution

It proposes a novel emergency-aware reasoning framework with RERAG and a type-agnostic traffic representation with R3, enhancing LLM-based TSC's reliability and generalization across heterogeneous intersections.

Findings

Reduces travel time by 42%

Decreases queue length by 62.31%

Cuts emergency vehicle waiting time by 83.16%

Abstract

With increasing urban traffic complexity, Traffic Signal Control (TSC) is essential for optimizing traffic flow and improving road safety. Large Language Models (LLMs) emerge as promising approaches for TSC. However, they are prone to hallucinations in emergencies, leading to unreliable decisions that may cause substantial delays for emergency vehicles. Moreover, diverse intersection types present substantial challenges for traffic state encoding and cross-intersection training, limiting generalization across heterogeneous intersections. Therefore, this paper proposes Retrieval Augmented Generation (RAG)-enhanced distributed LLM agents with Emergency response for Generalizable TSC (REG-TSC). Firstly, this paper presents an emergency-aware reasoning framework, which dynamically adjusts reasoning depth based on the emergency scenario and is equipped with a novel Reviewer-based Emergency RAG (RERAG) to distill specific knowledge and guidance from historical cases, enhancing the reliability and rationality of agents' emergency decisions. Secondly, this paper designs a type-agnostic traffic representation and proposes a Reward-guided Reinforced Refinement (R3) for heterogeneous intersections. R3 adaptively samples training experience from diverse intersections with environment feedback-based priority and fine-tunes LLM agents with a designed reward-weighted likelihood loss, guiding REG-TSC toward high-reward policies across heterogeneous intersections. On three real-world road networks with 17 to 177 heterogeneous intersections, extensive experiments show that REG-TSC reduces travel time by 42.00%, queue length by 62.31%, and emergency vehicle waiting time by 83.16%, outperforming other state-of-the-art methods.