Agentic AI-Based Joint Computing and Networking via Mixture of Experts and Large Language Models
For 6G network operators, this work provides a scalable method to dynamically orchestrate specialized optimization experts using high-level intents, though it is an incremental integration of existing techniques.
The paper proposes an agentic AI framework combining mixture of experts (MoE) with large language models (LLMs) for joint computing and networking in 6G. The framework achieves near-optimal performance compared to exhaustive expert combinations and outperforms individual experts in delay minimization and throughput maximization.
Future sixth-generation (6G) mobile networks are envisioned to be equipped with a diverse set of powerful, yet highly specialized, optimization experts. Such a promising vision is concurrently expected to give rise to the need for scalable mechanisms that can select, combine, and orchestrate such experts based on high-level intent and uncertainty descriptions. In this paper, we propose an agentic artificial intelligence (AI)-based network optimization framework that integrates mixture of experts (MoE) architectures with large language models (LLMs). Under the proposed framework, the employed LLM acts as a semantic gate to reason over operator objectives and dynamically compose suitable optimization agents. The proposed framework is formulated in a model-agnostic manner and bridges human-readable network intents with low-level resource allocation decisions, enabling flexible optimization across heterogeneous objectives and operating conditions. As a representative instantiation, we apply the framework to a joint communication and computing network and design a library of specialized optimization experts covering throughput, fairness, and delay-driven objectives under both regular and robust conditions. Numerical simulations demonstrate that the proposed agentic MoE framework consistently achieves near-optimal performance compared to exhaustive expert combinations while outperforming individual experts across diverse objectives, including delay minimization and throughput maximization.