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

2025-10-30

AI Summary

To address two critical bottlenecks in applying large language models (LLMs) to traffic signal control (TSC)—prone hallucination in emergency decision-making and poor generalization across heterogeneous intersections—this paper proposes a distributed LLM agent framework integrated with retrieval-augmented generation (RAG). It introduces a review-driven emergency retrieval module that dynamically retrieves historical emergency cases to enhance decision reliability and interpretability. Additionally, a reward-guided reinforcement refinement mechanism is proposed, combining type-agnostic traffic representation with experience-prioritized sampling to enable cross-intersection policy transfer. Experiments on three real-world road networks demonstrate significant improvements: average travel time reduced by 42.00%, queue length decreased by 62.31%, and emergency vehicle waiting time shortened by 83.16%, consistently outperforming state-of-the-art methods.

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
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Addresses unreliable LLM decisions for emergency vehicles in traffic control
• Solves generalization challenges across diverse intersection types
• Enhances traffic signal control reliability during emergency scenarios

Innovation

• RAG-enhanced LLM agents for emergency-aware traffic control
• Type-agnostic traffic representation with reward-guided refinement
• Reviewer-based Emergency RAG distills knowledge from historical cases