WMAS: A Multi-Agent System Towards Intelligent and Customized Wireless Networks

TL;DR

This paper introduces WMAS, a multi-agent system that uses reinforcement learning to optimize conversation topologies, enabling intelligent, customized wireless network services with high accuracy and low overhead.

Contribution

It proposes a novel reinforcement learning approach to optimize multi-agent conversation topologies modeled as directed acyclic graphs for wireless networks.

Findings

WMAS achieves higher task performance than existing systems.

WMAS reduces conversation overhead significantly.

Simulation results validate the effectiveness of the approach.

Abstract

The fast development of Artificial Intelligence (AI) agents provides a promising way for the realization of intelligent and customized wireless networks. In this paper, we propose a Wireless Multi-Agent System (WMAS), which can provide intelligent and customized services for different user equipment (UEs). Note that orchestrating multiple agents carries the risk of malfunction, and multi-agent conversations may fall into infinite loops. It is thus crucial to design a conversation topology for WMAS that enables agents to complete UE task requests with high accuracy and low conversation overhead. To address this issue, we model the multi-agent conversation topology as a directed acyclic graph and propose a reinforcement learning-based algorithm to optimize the adjacency matrix of this graph. As such, WMAS is capable of generating and self-optimizing multi-agent conversation topologies, enabling agents to effectively and collaboratively handle a variety of task requests from UEs. Simulation results across various task types demonstrate that WMAS can achieve higher task performance and lower conversation overhead compared to existing multi-agent systems. These results validate the potential of WMAS to enhance the intelligence of future wireless networks.