Agentic AI Empowered Intent-Based Networking for 6G

TL;DR

The paper tackles translating unstructured natural-language network intents into executable 6G network configurations by proposing a hierarchical agentic AI framework. An orchestrator agent coordinates two domain-specific specialists (RAN and Core) via ReAct-style iterative reasoning to generate feasible network slice provisioning under QoS constraints, grounded in a structured network state. A hybrid evaluation framework combining Semantic Accuracy and Engineering Utility demonstrates superior performance over baselines, while ablation studies reveal iterative reasoning and prompt engineering as the main drivers of improvement and highlight prompt-induced biases requiring careful validation. The work has practical implications for autonomous orchestration in Open RAN-like deployments, offering interpretable reasoning traces and modular design that supports safe, auditable decision-making in next-generation wireless systems.

Abstract

The transition towards sixth-generation (6G) wireless networks necessitates autonomous orchestration mechanisms capable of translating high-level operational intents into executable network configurations. Existing approaches to Intent-Based Networking (IBN) rely upon either rule-based systems that struggle with linguistic variation or end-to-end neural models that lack interpretability and fail to enforce operational constraints. This paper presents a hierarchical multi-agent framework where Large Language Model (LLM) based agents autonomously decompose natural language intents, consult domain-specific specialists, and synthesise technically feasible network slice configurations through iterative reasoning-action (ReAct) cycles. The proposed architecture employs an orchestrator agent coordinating two specialist agents, i.e., Radio Access Network (RAN) and Core Network agents, via ReAct-style reasoning, grounded in structured network state representations. Experimental evaluation across diverse benchmark scenarios shows that the proposed system outperforms rule-based systems and direct LLM prompting, with architectural principles applicable to Open RAN (O-RAN) deployments. The results also demonstrate that whilst contemporary LLMs possess general telecommunications knowledge, network automation requires careful prompt engineering to encode context-dependent decision thresholds, advancing autonomous orchestration capabilities for next-generation wireless systems.

Figures (3)

• Figure 1: Network system model illustration showing RAN sectors characterised by load $L_r$, active users $U_r$, and spectrum availability $B_r$, alongside core nodes characterised by compute load $\kappa_c$ and tier $\theta_c$. The latency matrix $\mathbf{T}$ captures end-to-end latency $\tau(r,c)$ between each sector-node pair.
• Figure 2: Hierarchical multi-agent architecture for IBN orchestration.
• Figure 3: Sequential coordination protocol for multi-domain network slice provisioning.