LLM-Powered Agentic AI for 5G/6G Networks: A Tutorial and Survey on Architectures, Protocols, and Standardization

2026-07-17 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Emerging Technologies & Innovation · Depth: Advanced, quick

Summary

Agentic Artificial Intelligence (AI), powered by Large Language Models (LLMs), represents a significant evolution from rule-based automation towards autonomous, goal-driven control within Next-Generation Networks (NGNs), specifically 5G and 6G. A new two-part tutorial and survey addresses the current gap where existing research often treats agentic AI and NGNs in isolation, overlooking crucial aspects like protocol integration, system evaluation, and standardization alignment. Part I of this work formalizes the control, management, and AI-native planes of 5G and 6G, then delves into the foundational elements of agentic systems, including reasoning, planning, tool use, multi-agent coordination, and evaluation methodologies. Part II subsequently maps these agentic capabilities onto 5G/6G control surfaces, relevant standardization efforts, and major 6G initiatives, concluding by identifying key open challenges that are currently shaping the future of autonomous telecommunications.

Key takeaway

For AI Architects and Research Scientists designing or evaluating next-generation network control systems, this survey highlights the critical shift towards LLM-powered agentic AI for autonomous 5G/6G management. You should prioritize understanding how agentic capabilities, including reasoning and multi-agent coordination, map onto existing 5G/6G control surfaces. Focus on integrating these systems with current protocols, establishing robust evaluation frameworks, and aligning solutions with ongoing standardization efforts to address identified open challenges effectively.

Key insights

The paper integrates LLM-powered agentic AI with 5G/6G networks, bridging gaps in protocol, evaluation, and standardization.

Principles

• Agentic AI shifts NGNs to goal-driven control.
• Foundational agentic systems include reasoning, planning, tool use.
• Multi-agent coordination is key for autonomous networks.

Method

The tutorial-and-survey formalizes 5G/6G planes, covers agentic system foundations (reasoning, planning, tool use, multi-agent coordination, evaluation), then maps capabilities to 5G/6G control surfaces and standardization.

In practice

• Apply agentic systems to 5G/6G control.
• Integrate LLMs for autonomous network management.
• Align agentic solutions with 6G initiatives.

Topics

• LLM-Powered AI
• Agentic Systems
• 5G Networks
• 6G Networks
• Network Automation
• Telecommunications Standardization
• Multi-Agent Coordination

Best for: AI Scientist, AI Architect, Research Scientist

Related on AIssential

• Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6G — AI-native 6G will shift from task-specific models to a foundation model and multi-agent systems for unified network optimization.
• Article: Multi-Agent AI for Production Security Operations: An A2A and MCP Architecture in a 5G Core — Multi-agent AI with policy-gated autonomy and anomaly-gated inference significantly enhances 5G core security operations.
• From Agentic to Autogenic Network Management for AI-Native 6G and Beyond: A Standards Perspective — Autogenic network management extends Agentic AI with self-programming and self-reflection for autonomous 6G network evolution.
• The AI Telco Engineer: Toward Autonomous Discovery of Wireless Communications Algorithms — Agentic AI frameworks can autonomously design and refine competitive, explainable wireless communication algorithms.
• Agentic AI for Manufacturing: Fragmented Data & LLM Reasoning Challenges — Agentic AI enhances industrial IoT by enabling natural language querying and autonomous reasoning over fragmented sensor data.
• AI-powered 6G core network reaches autonomous control with 40% efficiency gain — AI-powered 6G core networks can achieve autonomous control and significant efficiency gains, as demonstrated by a Korean research team.

See Counsel's argued verdicts on the open AI decisions leaders are weighing →

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.