An Agentic AI Control Plane for 6G Network Slice Orchestration, Monitoring, and Trading

TL;DR

This work addresses the challenge of building an AI-native, intent-driven control plane for 6G network slicing by unifying orchestration, monitoring, and trading under a cooperative agentic AI architecture. It proposes a five-layer architecture with an AI agents layer, a multi-model LLM consortium, and a Model Context Protocol interface to enable safe, intent-based interaction and governance. The approach combines market-aware resource allocation with continuous SLA assurance, implemented on a Kubernetes-based deployment and evaluated on a real-world testbed integrating Open5GS cores with Ericsson RAN. Results demonstrate feasible, explainable, and auditable autonomous slice management, signaling a practical path toward scalable 6G-native network slicing.

Abstract

6G networks are expected to be AI-native, intent-driven, and economically programmable, requiring fundamentally new approaches to network slice orchestration. Existing slicing frameworks, largely designed for 5G, rely on static policies and manual workflows and are ill-suited for the dynamic, multi-domain, and service-centric nature of emerging 6G environments. In this paper, we propose an agentic AI control plane architecture for 6G network slice orchestration, monitoring, and trading that treats orchestration as a holistic control function encompassing slice planning, deployment, continuous monitoring, and economically informed decision-making. The proposed control plane is realized as a layered architecture in which multiple cooperating AI agents. To support flexible and on-demand slice utilization, the control plane incorporates market-aware orchestration capabilities, allowing slice requirements, pricing, and availability to be jointly considered during orchestration decisions. A natural language interface, implemented using the Model Context Protocol (MCP), enables users and applications to interact with control-plane functions through intent-based queries while enforcing safety and policy constraints. To ensure responsible and explainable autonomy, the control plane integrates fine-tuned large language models organized as a multi-model consortium, governed by a dedicated reasoning model. The proposed approach is evaluated using a real-world testbed with multiple mobile core instances (e.g Open5GS) integrated with Ericsson's RAN infrastructure. The results demonstrate that combining agentic autonomy, closed-loop SLA assurance, market-aware orchestration, and natural language control enables a scalable and adaptive 6G-native control plane for network slice management, highlighting the potential of agentic AI as a foundational mechanism for future 6G networks.

Figures (10)

• Figure 1: Layered architecture of the proposed agentic AI control plane for 6G network slice orchestration, monitoring, and trading.
• Figure 2: Agentic control-plane flow illustrating intent-based slice orchestration, planning, execution, monitoring, and governance across cooperating AI agents.
• Figure 3: Responsible AI governance architecture based on a multi-model LLM consortium and a reasoning layer.
• Figure 4: Proposed testbed architecture integrating Ericsson’s next-generation RAN, multiple Open5GS mobile core instances, and on-premise LLM infrastructure deployed at VMASC, Virginia, USA.
• Figure 5: Fine-tuning evaluation metrics showing validation loss convergence and evaluation runtime stability for the Qwen2.