Optimizing Generative AI Networking: A Dual Perspective with Multi-Agent Systems and Mixture of Experts

Ruichen Zhang, Hongyang Du, Dusit Niyato, Jiawen Kang, Zehui Xiong, Ping Zhang, and Dong In Kim
Nanyang Technological University
Paper arXiv

Abstract

In the continued development of next-generation networking and artificial intelligence content generation (AIGC) services, the integration of multi-agent systems (MAS) and the mixture of experts (MoE) frameworks is becoming increasingly important. Motivated by this, this article studies the contrasting and converging of MAS and MoE in AIGC-enabled networking. First, we discuss the architectural designs, operational procedures, and inherent advantages of using MAS and MoE in generative AI to explore its functionality and applications fully. Next, we review the applications of MAS and MoE frameworks in content generation and resource allocation, emphasizing their impact on networking operations. Subsequently, we propose a novel multi-agent-enabled MoE-proximal policy optimization (MoE-PPO) framework for 3D object generation and data transfer scenarios. The framework uses MAS for dynamic task coordination of each network service provider agent and MoE for expert-driven execution of respective tasks, thereby improving overall system efficiency and adaptability. The simulation results demonstrate the effectiveness of our proposed framework and significantly improve the performance indicators under different network conditions. Finally, we outline potential future research directions.

BibTeX

@article{zhang2024optimizing,
  title={Optimizing Generative AI Networking: A Dual Perspective with Multi-Agent Systems and Mixture of Experts},
  author={Zhang, Ruichen and Du, Hongyang and Niyato, Dusit and Kang, Jiawen and Xiong, Zehui and Zhang, Ping and Kim, Dong In},
  journal={arXiv preprint arXiv:2405.12472},
  year={2024}
}