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

2026-05-02

AI Summary

This work addresses the limitations of current 6G network architectures, which are predominantly optimization-driven and lack the advanced reasoning capabilities required for autonomous intelligence. To bridge this gap, the paper proposes an agent-native network architecture for 6G that constructs a semantic control plane over deterministic infrastructure and systematically integrates large language model (LLM)-driven policy-constrained agents to enable distributed multi-agent collaborative reasoning and orchestration across device, edge, and core layers. The authors innovatively design a four-layer agent-native structure, uncovering a fundamental trade-off between reasoning capability and system efficiency, and advocate a heterogeneous deployment strategy spanning end devices, edge nodes, and cloud resources. Experimental results demonstrate that no single model can simultaneously satisfy latency, throughput, and accuracy requirements, and that quantization efficacy varies significantly across models, thereby validating the necessity of system-level cooperative optimization.

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.

Problem

• 6G
• Agentic AI
• Autonomous Intelligence
• Large Language Models
• Semantic Control Plane

Innovation

• Agentic AI
• AI-Native 6G
• Large Language Model (LLM)
• Semantic Control Plane
• Heterogeneous Deployment