catalysts logo

Gain access to resources and project updates

Register or log in to save your details for future use
First name
Last name
Business email
Company name
Job title

TM Forum will be processing the above information, with the assistance of our service providers located within and outside the European Union, to manage your registration to this event or report download, as well as to keep you informed about our services and products, future events and special offers, the organization of events, providing training and certification, and facilitating collaboration programs. Privacy policy

I wish to receive further information from the Catalyst Team about their products and service by electronic means. Check the "Team Members" section of this Catalyst Project to review the companies that will receive your information. Companies may join the project in the future, so please check back periodically for any updates

logologo
All Moonshots

L4 Autonomous Networks: Agent-powered zero-touch workflows

URN M25.0.832
Topics AI (Artificial Intelligence), Autonomous networks, Intent-based networking

Agent-powered end-to-end automation: Pioneering the autonomous network 'dark factory'

featured image
This Catalyst advances Level 4 autonomous networks through agent-led, zero-touch workflows that enable fully automated, end-to-end operations. As CSPs scale digital infrastructure, complexity and operational demand increase. Intelligent agents can address this challenge by orchestrating tasks with minimal intervention, reducing cost and accelerating resolution. The solution consists of two use cases. The first is a fault handling agent which provides real-time network situational awareness and automated remediation. By processing high-volume data in context, it identifies issues early, executes corrective actions, and significantly reduces mean time to repair. The second, a wireless network optimization agent, adapts to live network and user conditions, executing precision adjustments that improve signal quality and reduce manual tuning. These agents operate as an execution framework layered with AI, task planning, and domain knowledge. Unlike standalone AI models, agents manage goal-setting, resource selection, and tool orchestration across closed-loop processes. This 'lights-out factory' approach transforms network operations—removing routine human input while maintaining transparency and control. The project applies and contributes to TM Forum assets, including the Autonomous Networks (AN) series. Agent-led workflows enable faster, more accurate fault resolution, reduce service interruptions, and improve network efficiency. They also support targeted, localized optimization at scale—enhancing user experience without increasing operational burden. Performance will be assessed through KPIs such as reduced MTTR, improved coverage, increased throughput, and lower complaint volumes. By deploying AI agents as decision-making and execution tools, this Catalyst demonstrates a viable path to scalable Level 4 autonomy—unlocking a new standard for operational agility, service reliability, and network intelligence.

Contact team

Email the members of the Catalyst team to request more details.

Name
Email

Team members

AsiaInfo Technologies (China), Inc. logo
Beijing Ultrapower Software Co., Ltd. logo
Beijing ZZNode Technologies Co.,Ltd. logo
China Academy of Information and Communications Technology(CAICT) logo
Champion
China Mobile Communications Corporation logo
Champion
Huawei Technologies Co. Ltd logo
Inspur Communication Information Systems Co., Ltd logo
ZTE Corporation logo

Related projects