Gain access to resources and project updates

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

I agree to the tmforum.org Terms and Conditions of Use

All projects

AI agent empowering higher autonomous level

URN C24.0.672

Topics AI (Artificial Intelligence), Autonomous networks, Open Digital Architecture (ODA)

Making network operations more accessible with large language models

Project companies

The telecom industry faces a dual challenge: On one hand, increasing network and operational complexity, and the need for customer-centricity. Existing solutions have been proven inadequate, leading to higher costs and customer dissatisfaction. On the other hand, the rise of Large Language Models (LLMs) and AI agents presents a transformative opportunity. The telecom operators can leverage these innovations to revolutionize network operations and customer experience. But the path to successful adoption and integration is not without hurdles. Telecom operators must navigate the complexities of adapting these innovations to their existing systems and processes to pave the way to their transformation into techcos. The catalyst project members conclude the Industry consensus that LLM-based AI Agent is the key to address the challenges and A collaborative and innovative approach to adopt this advanced technology is crucial. We will pioneer a LLM-based AI Agent, utilizing a network digital twin to amalgamate insights from current systems. The agent will autonomously execute complex tasks using AIOps. LLM will interpret user intents, deconstruct tasks, and deliver optimal solutions, propelling us towards scope autonomy and a target-driven model. To address adoption and integration challenges, we will develop a phased approach, starting with a proof of concept and gradually expanding to full-scale implementation. Our team will collaborate closely with stakeholders across the organization to ensure seamless integration with existing systems and processes. Our approach aligns with Open Digital Architecture (ODA) standards, ensuring scalability and adoptability by other telcos. During this project, the following business cases will be explored to assess and refine the capabilities of the LLM-based AI Agent: Home Broadband Self-Service from China Telecom: Implementing AI agent for automated customer support in self-service platforms; Customer Complaint Handling from China Telecom: Utilizing AI agent to enhance the efficiency of complaint resolution processes within the NOC back office; High-Value User Experience Assurance from HKT: Leveraging AI to proactively manage and assure service quality for high-value customers. AI Agent empowers telcos' higher autonomous level, revolutionizing operations, reducing costs, and boosting customer satisfaction. By setting a best practice for revolutionizing network operations and customer experience, we aim to inspire the industry to embrace AI-driven solutions, unlocking new opportunities for enhanced efficiency and revenue growth.

Resources

AI Agents transforming telecom: Efficiency, experience, and beyond. Welcome to join us at C12 booth in Hall 3 for details! CSPs face growing challenges in driving business growth while managing increasingly complex operations. Current siloed AI deployments limit efficiency, hinder ROI assessment, and create barriers to staff engagement with AI. The rise of Large Language Models (LLMs) and AI agents presents a transformative opportunity to address these challenges. However, they also present unique technical obstacles, such as reconciling the deterministic requirements of applications with the inherent uncertainty of LLM outputs, enhancing LLMs' accuracy in complex task planning, and improving their ability to continuously reflect and adapt during execution. Participating operators and vendors have reached an industry consensus that LLM-based AI agents are the key to tackling these issues. They also point out that operators need a systematic approach to guide the application of this advanced technology in production to achieve goals such as improving operational efficiency, enhancing customer experience, and exploring rapidly evolving demands, ultimately reaching a new level of autonomous operations. This innovative project pioneers the introduction of an LLM-based AI agent implementation framework and technical architecture, promoting the seamless integration of LLMs and AI agents with telecom operator processes. The implementation framework includes the VOF value model and execution system, adhering to industry standards such as ODA, AIOps, DT4DI, and AOMM, ensuring scalability and adaptability in telecom business cases. The technical architecture applies the operator's digital twins and domain knowledge to large model training. The framework proposes the use of engineering methods to effectively reduce AI agent hallucination and lower the threshold for business personnel to write agents, greatly improving the reliability and usability of AI agents and making them applicable to multiple value streams in telecom operations, maintenance, and customer experience management. In this project, China Telecom and HKT conducted pilots in areas such as broadband home self-service, customer complaint handling, and VVIP user experience assurance, achieving tangible results in operational efficiency improvement, operational cost savings, and customer satisfaction enhancement. Operators plan to extend the solution to support a wider range of areas, including new business development, stable and secure operations, operational efficiency improvement, and green energy-saving initiatives. This project sets a new benchmark for best practices for other telecom operators and vendors. Furthermore, participants are actively collaborating to participate in TM Forum standard construction, promoting broader industry cooperation and encouraging more partners to embark on this transformative journey together.