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

TL;DR

This paper advocates for a paradigm shift in 6G networks towards agentic AI-native architectures utilizing LLM-based agents for reasoning, demonstrating a multi-layer framework and empirical tradeoffs in system performance.

Contribution

It introduces a novel four-layer architecture for agentic 6G networks, integrating reasoning and multi-agent coordination, supported by a proof-of-concept framework and empirical analysis.

Findings

Heterogeneous deployment of LLM agents balances latency, throughput, and accuracy.

Quantization effects vary across models, affecting system optimization.

No single model satisfies all performance constraints simultaneously.

Abstract

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.