1、Ericsson White PaperBCSS-25:024439October 2025White paper AI agents in the telecommunication network architectureWhite paper AI agents in the telecommunication network architectureContentOctober 20252ContentIntroduction 3AI agents:definition and taxonomy 4The AI journey and the network transformatio
2、n 6AI agents and network architecture 8Model Context Protocol 13Agent-to-agent in the telecommunications domain 15Robustness and trustworthiness in AI agent-based systems 16Summary 17Conclusion 19References 20White paper AI agents in the telecommunication network architectureIntroduction October 202
3、53Introduction The journey toward autonomous networks has been long underway,but has only recently started accelerating significantly.AI agents,generative AI(GenAI),and large language models(LLMs)are predicted to become key components for enhancing network efficiency,customer service,and operational
4、 management due to their strong autonomous capabilities.In this white paper,we define AI agents and provide an example of their use in the mobile network architecture,with the TM Forum-specified intent management architecture serving as the main case study.We also investigate other possible use case
5、s,such as enabling mobile networks to optimize communication between agents used by subscribers and enterprises.We will explore and discuss concepts and analyses introduced in previous white papers,including Defining AI native:A key enabler for advanced intelligent telecom networks 1,Intent-driven n
6、etworks is a key step in the journey to autonomous networks 5,and Cognitive reasoning for 5G network lifecycle management 2.White paper AI agents in the telecommunication network architectureAI agents:Definition and taxonomyOctober 20254AI agents:Definition and taxonomyIn response to the large numbe