Saved in:
Bibliographic Details
Main Authors: Wu, Binghan, Wang, Shoufeng, Liu, Yunxin, Zhang, Ya-Qin, Sifakis, Joseph, Ouyang, Ye
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.08312
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912862378655744
author Wu, Binghan
Wang, Shoufeng
Liu, Yunxin
Zhang, Ya-Qin
Sifakis, Joseph
Ouyang, Ye
author_facet Wu, Binghan
Wang, Shoufeng
Liu, Yunxin
Zhang, Ya-Qin
Sifakis, Joseph
Ouyang, Ye
contents The evolution toward Level 4 (L4) Autonomous Networks (AN) represents a strategic inflection point in telecommunications, where networks must transcend reactive automation to achieve genuine cognitive capabilities--fulfilling TM Forum's vision of self-configuring, self-healing, and self-optimizing systems that deliver zero-wait, zero-touch, and zero-fault services. This work bridges the gap between architectural theory and operational reality by implementing Joseph Sifakis's AN Agent reference architecture in a functional cognitive system, deploying coordinated proactive-reactive runtimes driven by hybrid knowledge representation. Through an empirical case study of a Radio Access Network (RAN) Link Adaptation (LA) Agent, we validate this framework's transformative potential: demonstrating sub-10 ms real-time control in 5G NR sub-6 GHz while achieving 4% higher downlink throughput than Outer Loop Link Adaptation (OLLA) algorithms and 85% Block Error Rate (BLER) reduction for ultra-reliable services through dynamic Modulation and Coding Scheme (MCS) optimization. These improvements confirm the architecture's viability in overcoming traditional autonomy barriers and advancing critical L4-enabling capabilities toward next-generation objectives.
format Preprint
id arxiv_https___arxiv_org_abs_2509_08312
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging AI Agents for Autonomous Networks: A Reference Architecture and Empirical Studies
Wu, Binghan
Wang, Shoufeng
Liu, Yunxin
Zhang, Ya-Qin
Sifakis, Joseph
Ouyang, Ye
Artificial Intelligence
The evolution toward Level 4 (L4) Autonomous Networks (AN) represents a strategic inflection point in telecommunications, where networks must transcend reactive automation to achieve genuine cognitive capabilities--fulfilling TM Forum's vision of self-configuring, self-healing, and self-optimizing systems that deliver zero-wait, zero-touch, and zero-fault services. This work bridges the gap between architectural theory and operational reality by implementing Joseph Sifakis's AN Agent reference architecture in a functional cognitive system, deploying coordinated proactive-reactive runtimes driven by hybrid knowledge representation. Through an empirical case study of a Radio Access Network (RAN) Link Adaptation (LA) Agent, we validate this framework's transformative potential: demonstrating sub-10 ms real-time control in 5G NR sub-6 GHz while achieving 4% higher downlink throughput than Outer Loop Link Adaptation (OLLA) algorithms and 85% Block Error Rate (BLER) reduction for ultra-reliable services through dynamic Modulation and Coding Scheme (MCS) optimization. These improvements confirm the architecture's viability in overcoming traditional autonomy barriers and advancing critical L4-enabling capabilities toward next-generation objectives.
title Leveraging AI Agents for Autonomous Networks: A Reference Architecture and Empirical Studies
topic Artificial Intelligence
url https://arxiv.org/abs/2509.08312