arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.01546cs.NIcs.AI
收藏

6G需要智能体：迈向面向自主智能的智能体AI原生网络

6G Needs Agents: Toward Agentic AI-Native Networks for Autonomous Intelligence

Department of Computer and Network Engineering, United Arab Emirates University, UAE（计算机与网络工程系，阿联酋大学）；Research Institute for Digital Future, Khalifa University, UAE（数字未来研究院，哈利法大学）

Mohamed Amine Ferrag, Abderrahmane Lakas, Merouane Debbah

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出基于大语言模型的智能体架构，用于构建AI原生6G网络，通过分层推理和分布式多智能体系统平衡性能与效率，揭示了模型异构部署和量化影响的重要性。

摘要：

第六代（6G）网络日益被设想为整合通信、传感和计算的AI原生基础设施。然而，现有方法仍以优化为中心，依赖闭环控制，具有有限的推理能力。本文主张向智能体AI原生6G范式转变，其中基于大语言模型（LLM）的智能体作为受政策约束的推理实体，在确定性3GPP基础设施之上运行于语义控制平面。我们提出四层架构，整合确定性网络基础设施、意图和上下文的语义抽象、分层推理以及跨设备、边缘和核心域的分布式多智能体系统。为评估可行性，我们开发了智能体推理和编排框架，并通过领域特定的6G基准进行广泛实证研究。结果揭示了推理能力与系统效率之间的根本权衡，表明没有单一模型能同时满足延迟、吞吐量和准确性要求。相反，异构部署LLM智能体跨设备-边缘-核心连续体是必要的，以平衡这些约束。我们进一步表明，量化在模型间引入非均匀影响，强化了系统级优化而非模型级压缩的必要性。这些发现确立了智能体智能作为6G可行的架构方向，并突显了实现可扩展、可信和自主网络的关键挑战。所有实验结果和评估脚本均已公开以支持可重复性。

英文摘要：

Sixth-generation (6G) networks are increasingly envisioned as AI-native infrastructures integrating communication, sensing, and computing into a unified fabric. However, existing approaches remain largely optimization-centric, relying on closed-loop control with limited reasoning capability. In this paper, we argue for a paradigm shift toward Agentic AI-Native 6G, in which Large Language Model (LLM)-based agents operate as bounded, policy-governed reasoning entities within a semantic control plane layered above deterministic 3GPP infrastructure. We propose a four-layer architecture that integrates deterministic network infrastructure, semantic abstraction of intent and context, hierarchical reasoning, and a distributed multi-agent fabric spanning device, edge, and core domains. To assess feasibility, we develop a proof-of-concept agentic reasoning and orchestration framework and conduct an extensive empirical study using a domain-specific 6G benchmark under realistic deployment constraints. Our results reveal a fundamental tradeoff between reasoning capability and system efficiency, showing that no single model simultaneously satisfies latency, throughput, and accuracy requirements. Instead, heterogeneous deployment of LLM agents across the device--edge--core continuum is necessary to balance these constraints. We further demonstrate that quantization introduces non-uniform effects across models, reinforcing the need for system-level optimization rather than model-level compression alone. These findings establish agentic intelligence as a viable architectural direction for 6G and highlight key challenges in achieving scalable, trustworthy, and self-reasoning networks. All experimental results and evaluation scripts are publicly available to support reproducibility.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑