Enhancing Secure Intent-Based Networking with an Agentic AI: The EU Project MARE Approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zacarias, Iulisloi, Grunewald, Marla, Gentzen, Fin, Masip-Bruin, Xavi, Jukan, Admela
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908947453050880
author Zacarias, Iulisloi
Grunewald, Marla
Gentzen, Fin
Masip-Bruin, Xavi
Jukan, Admela
author_facet Zacarias, Iulisloi
Grunewald, Marla
Gentzen, Fin
Masip-Bruin, Xavi
Jukan, Admela
contents In the EU project MARE, a novel plane was proposed and used in combination with intent-based networking (IBN), allowing the operator to focus on what, rather than on how. Recently, LLMs have been successfully employed to translate the high-level intents into low-level actions. The open challenge is to understand how IBN can be effectively enhanced with LLM and the emerging agentic AI for security purposes. Enhancing IBN with an agentic AI paradigm introduces significant challenges that existing solutions do not fully address. This paper proposes an enhanced IBN framework with a strong security focus toward agentic AI. We address the architectural and security requirements for a multi-agent intent-based system (IBS) architecture, including a multi-domain IBN. We propose a hierarchical multi-agent and multi-vendor architecture that can also be applied more broadly in 6G architectures and beyond, beyond the security architecture proposed in MARE. The architecture incorporates an interactive intent-processing pipeline using LLMs, and it also allows the IBS to connect to external security knowledge bases, such as MITRE ATT\&CK, MITRE FiGHT, and NIST.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06856
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhancing Secure Intent-Based Networking with an Agentic AI: The EU Project MARE Approach
Zacarias, Iulisloi
Grunewald, Marla
Gentzen, Fin
Masip-Bruin, Xavi
Jukan, Admela
Networking and Internet Architecture
In the EU project MARE, a novel plane was proposed and used in combination with intent-based networking (IBN), allowing the operator to focus on what, rather than on how. Recently, LLMs have been successfully employed to translate the high-level intents into low-level actions. The open challenge is to understand how IBN can be effectively enhanced with LLM and the emerging agentic AI for security purposes. Enhancing IBN with an agentic AI paradigm introduces significant challenges that existing solutions do not fully address. This paper proposes an enhanced IBN framework with a strong security focus toward agentic AI. We address the architectural and security requirements for a multi-agent intent-based system (IBS) architecture, including a multi-domain IBN. We propose a hierarchical multi-agent and multi-vendor architecture that can also be applied more broadly in 6G architectures and beyond, beyond the security architecture proposed in MARE. The architecture incorporates an interactive intent-processing pipeline using LLMs, and it also allows the IBS to connect to external security knowledge bases, such as MITRE ATT\&CK, MITRE FiGHT, and NIST.
title Enhancing Secure Intent-Based Networking with an Agentic AI: The EU Project MARE Approach
topic Networking and Internet Architecture
url https://arxiv.org/abs/2604.06856