Salvato in:
Dettagli Bibliografici
Autori principali: Taleb, Nabil Abdelaziz Ferhat, Rezaei, Abdolazim, Patel, Raj Atulkumar, Sookhak, Mehdi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.13511
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909694698717184
author Taleb, Nabil Abdelaziz Ferhat
Rezaei, Abdolazim
Patel, Raj Atulkumar
Sookhak, Mehdi
author_facet Taleb, Nabil Abdelaziz Ferhat
Rezaei, Abdolazim
Patel, Raj Atulkumar
Sookhak, Mehdi
contents Large Language Models (LLMs) offer significant promise for intelligent traffic management; however, current chain-based systems like TrafficGPT are hindered by sequential task execution, high token usage, and poor scalability, making them inefficient for complex, real-world scenarios. To address these limitations, we propose GraphTrafficGPT, a novel graph-based architecture, which fundamentally redesigns the task coordination process for LLM-driven traffic applications. GraphTrafficGPT represents tasks and their dependencies as nodes and edges in a directed graph, enabling efficient parallel execution and dynamic resource allocation. The main idea behind the proposed model is a Brain Agent that decomposes user queries, constructs optimized dependency graphs, and coordinates a network of specialized agents for data retrieval, analysis, visualization, and simulation. By introducing advanced context-aware token management and supporting concurrent multi-query processing, the proposed architecture handles interdependent tasks typical of modern urban mobility environments. Experimental results demonstrate that GraphTrafficGPT reduces token consumption by 50.2% and average response latency by 19.0% compared to TrafficGPT, while supporting simultaneous multi-query execution with up to 23.0% improvement in efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2507_13511
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GraphTrafficGPT: Enhancing Traffic Management Through Graph-Based AI Agent Coordination
Taleb, Nabil Abdelaziz Ferhat
Rezaei, Abdolazim
Patel, Raj Atulkumar
Sookhak, Mehdi
Artificial Intelligence
Large Language Models (LLMs) offer significant promise for intelligent traffic management; however, current chain-based systems like TrafficGPT are hindered by sequential task execution, high token usage, and poor scalability, making them inefficient for complex, real-world scenarios. To address these limitations, we propose GraphTrafficGPT, a novel graph-based architecture, which fundamentally redesigns the task coordination process for LLM-driven traffic applications. GraphTrafficGPT represents tasks and their dependencies as nodes and edges in a directed graph, enabling efficient parallel execution and dynamic resource allocation. The main idea behind the proposed model is a Brain Agent that decomposes user queries, constructs optimized dependency graphs, and coordinates a network of specialized agents for data retrieval, analysis, visualization, and simulation. By introducing advanced context-aware token management and supporting concurrent multi-query processing, the proposed architecture handles interdependent tasks typical of modern urban mobility environments. Experimental results demonstrate that GraphTrafficGPT reduces token consumption by 50.2% and average response latency by 19.0% compared to TrafficGPT, while supporting simultaneous multi-query execution with up to 23.0% improvement in efficiency.
title GraphTrafficGPT: Enhancing Traffic Management Through Graph-Based AI Agent Coordination
topic Artificial Intelligence
url https://arxiv.org/abs/2507.13511