电信网络架构中的AI智能体白皮书

Content Introduction3AI agents: definition and taxonomy4The AI journey and the network transformation6AI agents and network architecture8Model Context Protocol13Agent-to-agent in the telecommunications domain15Robustness and trustworthiness in AI agent-based systems16Summary17Conclusion19References20 Introduction The journey toward autonomous networks has been long underway, but has onlyrecently started accelerating significantly. AI agents, generative AI (GenAI), and largelanguage models (LLMs) are predicted to become key components for enhancingnetwork efficiency, customer service, and operational management due to their strongautonomous capabilities. In this white paper, we define AI agents and provide an example of their use inthe mobile network architecture, with the TM Forum-specified intent managementarchitecture serving as the main case study. We also investigate other possible usecases, such as enabling mobile networks to optimize communication between agentsused 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 networks is a key step in the journey to autonomous networks [5],and Cognitive reasoning for 5G network lifecycle management [2]. AI agents:Definition andtaxonomy In response to the large number of diverse interpretations of the roles and tasks of AI agentsin the network, we need to clarify what agents and AI agents are. Agent An agent is an autonomous system authorized to act, decide, and self-initiate tasksindependently on behalf of a person or entity. Guided by goals, an agent perceives its environment through mechanisms such as sensors,protocols, data streams, or interactions with other agents. It processes information usingrules, programmed logic, or learned models to produce outputs, take actions, use tools, oreven execute code to achieve its goals. Agents can interact with their environment in runtime and can store and retrieveinformation over time, act individually, or collaborate through agent-to-agentcommunication. Their computational expressivity spans deterministic rule-based behaviorto Turing-complete reasoning, enabling varied levels of adaptability, decision-making, andplanning. AI agents AI agents, a subclass of agents, leverage machine learning to update their internalknowledge, sometimes referred to as memory, enabling dynamic adaptation to changingconditions. They exist on a continuum ranging from restricted, bound by human-defined constraints,to unrestricted, capable of modifying their internal logic and goals. Though many roles andorganizational schemes exist, such as orchestrator-, coordinator-, and executor-agents, thistaxonomy focuses on classifying agents as AI or non-AI and restricted or unrestricted. This way, we can define the boundary between restricted and unrestricted agents, lettingus determine whether and where to allow different kinds of agents and how they should bereflected in the architecture. Although there can be all kinds of variations of these two agenttypes, at some point, a restricted agent becomes unrestricted in the following cases: •Modification of internal logic:Overriding human-programmed restrictions•Modification of goals:Lifting the boundaries of human-assigned goals A specific subtype of GenAI-based agents called a copilot is worth explicit mention here.It is a restricted, LLM-based agent designed to work interactively with humans as a human-to-machine interface. Copilots assist and enhance human performance by leveraging LLMs’advanced understanding of natural language. The AI journeyand the networktransformation The evolution of modern telecommunication networks, enriched by 5G and future 6Gtechnologies, has brought increased complexity and a critical need for automating networkoperations. Without automation, the cost of traditional network operations could becomeunsustainable, requiring vendors and communications service providers (CSPs) to addresssuch complexity. Automation addresses this need while also being an enabler for a moreversatile network that swiftly adjusts to evolving customer needs. AI can drive automation by leveraging the right data and by utilizing our deep expertise inthe most relevant network aspects. With these in place, AI can be embedded in the productportfolio to provide the greatest value across operational efficiency, customer experience,business growth, and sustainability. The synergy between AI and networks will become even more critical in 6G, where AIwill serve as a key native component, shaping the network architecture, capabilities, andservices, enabling intent-based management with minimal human intervention, andachieving zero-touch operations. At the same time, the emergence of new approaches such as GenAI and AI agents furtheramplifies these capabilities, showcasing potential applications across multiple domains,i