



Network Working Group                                        B. Sarikaya
Internet-Draft                                              Unaffiliated
Intended status: Standards Track                               R. Schott
Expires: 15 March 2026                                  Deutsche Telekom
                                                       11 September 2025


      AI Agents for 6G Requirements and Implementation Approaches
              draft-sarischo-6gip-aiagent-requirements-00

Abstract

   This document provides requirements for 3GPP Artificial Intelligence/
   Machine Learning (AI/ML) Agents for the 6th generation mobile
   network, or 6G.  Requirements depend on the types and application
   areas of agents.  We describe each type and state their requirements.
   AI Agent implementation efforts, how APIs can be discovered, how
   inter-domain and intra domain AI Agents can be discovered using DNS
   lookup are explained.

Status of This Memo

   This Internet-Draft is submitted in full conformance with the
   provisions of BCP 78 and BCP 79.

   Internet-Drafts are working documents of the Internet Engineering
   Task Force (IETF).  Note that other groups may also distribute
   working documents as Internet-Drafts.  The list of current Internet-
   Drafts is at https://datatracker.ietf.org/drafts/current/.

   Internet-Drafts are draft documents valid for a maximum of six months
   and may be updated, replaced, or obsoleted by other documents at any
   time.  It is inappropriate to use Internet-Drafts as reference
   material or to cite them other than as "work in progress."

   This Internet-Draft will expire on 15 March 2026.

Copyright Notice

   Copyright (c) 2025 IETF Trust and the persons identified as the
   document authors.  All rights reserved.










Sarikaya & Schott         Expires 15 March 2026                 [Page 1]

Internet-Draft         AI/ML  Agents requirements         September 2025


   This document is subject to BCP 78 and the IETF Trust's Legal
   Provisions Relating to IETF Documents (https://trustee.ietf.org/
   license-info) in effect on the date of publication of this document.
   Please review these documents carefully, as they describe your rights
   and restrictions with respect to this document.  Code Components
   extracted from this document must include Revised BSD License text as
   described in Section 4.e of the Trust Legal Provisions and are
   provided without warranty as described in the Revised BSD License.

Table of Contents

   1.  Introduction  . . . . . . . . . . . . . . . . . . . . . . . .   2
   2.  6G Network AI Agents  . . . . . . . . . . . . . . . . . . . .   3
     2.1.  AI Agents collaboration with third-party AI using LLM . .   4
     2.2.  AI Agents for Artificial General Intelligence . . . . . .   4
     2.3.  AI Agents on Device . . . . . . . . . . . . . . . . . . .   5
     2.4.  Collaborative AI Agents . . . . . . . . . . . . . . . . .   5
     2.5.  Home Robots . . . . . . . . . . . . . . . . . . . . . . .   6
     2.6.  Built-in Intelligent Communication Assistant  . . . . . .   6
   3.  Implementation Issues . . . . . . . . . . . . . . . . . . . .   7
     3.1.  Future Work . . . . . . . . . . . . . . . . . . . . . . .   8
   4.  Security Considerations . . . . . . . . . . . . . . . . . . .   8
   5.  IANA Considerations . . . . . . . . . . . . . . . . . . . . .   8
   6.  Acknowledgements  . . . . . . . . . . . . . . . . . . . . . .   8
   7.  References  . . . . . . . . . . . . . . . . . . . . . . . . .   8
     7.1.  Normative References  . . . . . . . . . . . . . . . . . .   8
     7.2.  Informative References  . . . . . . . . . . . . . . . . .   9
   Authors' Addresses  . . . . . . . . . . . . . . . . . . . . . . .  10

1.  Introduction

   Artificial Intelligence (AI) has historically been defined as the
   science and engineering to build intelligent machines capable of
   carrying out tasks as humans do.  Inspired from the way human brain
   works, machine learning (ML) is defined as the field of study that
   gives computers the ability to learn without being explicitly
   programmed.  Since it is believed that the main computational
   elements in a human brain are 86 billion neurons, the more popular ML
   approaches are using “neural network” as the model.  Neural networks
   (NN) take their inspiration from the notion that a neuron’s
   computation involves a weighted sum of the input values.  A
   computational neural network contains the neurons in the input layer
   which receive some values and propagate them to the neurons in the
   middle layer of the network, which is also called a “hidden layer”.
   The weighted sums from one or more hidden layers are ultimately
   propagated to the output layer, which presents the final outputs of
   the network.




Sarikaya & Schott         Expires 15 March 2026                 [Page 2]

Internet-Draft         AI/ML  Agents requirements         September 2025


   Recurrent neural network (RNN) models are a type of deep neural
   networks which use sequential data feeding.  The input of RNN
   consists of the current input and the previous samples.  RNN models
   recently have been replaced with parallel processing [LLMPaper] and
   the transformer architecture and they are being used in the natural
   language processing task on mobile devices, e.g., language modeling,
   machine translation, question answering, word embedding, and document
   classification.  The resulting system is commonly called Large
   Language Model (LLM).

   AI Agents play a crucial role in modern telecommunications by
   enabling intelligent automation, decision-making, and adaptive
   network management.  These agents are software-driven entities that
   leverage artificial intelligence, including machine learning and
   natural language processing, to interact with users, applications,
   and network components.  In a 6G environment, AI agents enhance
   network efficiency by dynamically optimizing resources, predicting
   network conditions, and facilitating providing seamless communication
   between services.  By integrating Large Language Models (LLM), AI
   agents can understand complex requests, translate them into
   actionable insights, and orchestrate 3GPP services (e.g.
   communication service, sensing service, AI-related) network
   capabilities and functions autonomously, ultimately improving user
   experience when consuming the 3GPP services, operational efficiency,
   and service innovation.

   This document aims to present the types of AI agents 6G network needs
   and the requirements needed to support each case.  We discuss
   implementation issues next.

   In a related work, [aiagent6g] attempts to analyze the agent protocol
   requirements and relevant enabling technologies based on 6G mobile
   communication system specific characteristics.

   On the other hand [aiagentusecase] introduces use cases and
   requirements on AI Agents in 6G networks.  It attempts to elaborate
   on the requirements for high performance communication, security and
   energy efficiency.

2.  6G Network AI Agents

   The following use cases and requirements are from [TR22.870].









Sarikaya & Schott         Expires 15 March 2026                 [Page 3]

Internet-Draft         AI/ML  Agents requirements         September 2025


2.1.  AI Agents collaboration with third-party AI using LLM

   A third-party application (e.g. a smart city traffic management
   system) AI Agent sends a text-based request or query to the 6G
   network.  The request is processed by an AI agent in the 6G network
   that leverages LLMs and the network's advanced capabilities (e.g.
   sensing, real-time data processing, telemetry, analytics, and others)
   to provide a response or perform an action.  This interaction mimics
   how users interact with chatbots like ChatGPT, but it is tailored for
   network-specific tasks and applications.

   *  Requirements

   The network shall be able to support secure means to expose its
   services to the authorised third-party AI agent based on its intent.

   The network shall be able to take into account information related to
   user mobility context, subscription information when invoking 3GPP
   services based on user intent(s).

2.2.  AI Agents for Artificial General Intelligence

   Autonomous agents (AI agents) have long been recognized as a
   promising approach to achieving artificial general intelligence
   (AGI), which is expected to accomplish tasks through self-directed
   planning and actions.  In recent years, these agents, leveraging the
   capabilities of LLMs, are expected to effectively perform diverse
   tasks in social science, natural science, and engineering, among
   others.  AI agents can take on various forms, such as embodied
   intelligent robots, virtual assistants, and autonomous systems (e.g.
   drones).

   *  Requirements

   The network shall support trusted network access for 3rd party AI
   agent and support a mechanism to expose 3rd party AI agent’s
   attributes (e.g. related users, sensing capabilities, AI
   capabilities, service features) to other 3rd party AI agents.

   The network shall be able to support security identification for 3rd
   party AI agents provided by authorized 3rd party associated with a
   user (e.g. AI agents belonging to a customer).

   The network shall support mechanisms for 3rd party AI agents to
   provide/register their attributes (e.g. sensing capabilities, AI
   capabilities, service features, associated authorized users) to 6G
   network, and discover other authorized 3rd party AI agents to achieve
   collaborative task.



Sarikaya & Schott         Expires 15 March 2026                 [Page 4]

Internet-Draft         AI/ML  Agents requirements         September 2025


   The network shall provide means to support efficient and secure
   communication between 3rd party AI agents over a wide area in a group
   considering the diverse lifetime of tasks.

2.3.  AI Agents on Device

   AI agent on device will be popular in 6G era, due to the fast
   development on device-based computing power and model light-
   weighting.

   *  Requirements

   The system shall provide a suitable means for an AI agent application
   on UE to invoke some 3GPP services (e.g. IMS service).

   The system shall provide an efficient way to expose information (e.g.
   change of QoS) to the application on the UE.

   The network shall be able to support the message exchange between the
   AI agent application on different UEs considering the diverse
   capabilities supported by different AI applications (e.g. AI agents
   applications).

2.4.  Collaborative AI Agents

   AI Agents can perform tasks for or represent e.g. devices, persons,
   drones, or cars.  These AI Agents may be either implemented in a UE
   or in the network.  By offloading tasks to the network, devices can
   save on complexity and energy consumption.  Furthermore, an AI Agent
   in the network can still represent a device, person, drone or car,
   when that device, person, drone or car is not reachable, e.g. because
   of radio conditions or battery outage.  Offload can happen towards a
   local/edge network but can also be to a nearby other device with more
   processing capabilities.

   *  Requirements

   The system shall support hosting of large amounts of AI agent
   applications managed and controlled by the 6G core network and/or
   multiple AI Agent applications on a UE.

   The system shall support secure interoperability between AI Agents
   and between AI Agents and applications to achieve a collaborative
   task.







Sarikaya & Schott         Expires 15 March 2026                 [Page 5]

Internet-Draft         AI/ML  Agents requirements         September 2025


2.5.  Home Robots

   Home robots will engage in household chores based on preconfigured
   models, such as sweeping the floor, vacuuming, folding clothes,
   washing dishes, and organizing rooms.  They will also take care of
   family members by monitoring health data, reminding medication, and
   dialling emergency calls.  Additionally, they will socialize and
   entertain with humans while interacting with other smart devices to
   create a more intelligent ecosystem.  All of this aims to bring us a
   more convenient, comfortable, and safe family life.  All or part of
   the AI inference services are provided by home robots.

   *  Requirements

   The network shall be able to provide AI service (e.g. AI model
   inference) to a UE.

   The system shall be able to support negotiation of the service
   performance (e.g. latency, inference accuracy), between UE and 6G
   network, when providing AI service (e.g. AI model inference).

   The network shall be able to support mechanism to guarantee the
   service performance (e.g. latency, inference accuracy) when providing
   AI service (e.g. AI model inference).

2.6.  Built-in Intelligent Communication Assistant

   Empowered by the rapid development of the AI technology, the service
   providers are able to provide personalized and enriched services to
   their users when making daily routines within their homes, at their
   workplaces, in stores, at restaurants, as well as traveling for work
   or leisure.  These kinds of personalized services are widely enjoyed
   by the customers.  For example, a lot of countries are facing a major
   challenge in providing care support for senior citizens due to their
   rapidly ageing population and declining old-age support.  The
   capability to introduce AI techs to provide more personalized and
   real-time communication services would be a great help.

   *  Requirements

   The network (e.g. in conjunction to IMS) shall be able to provide
   intelligent communication assistant service to users.

   The network shall support charging information collection for the
   intelligent communication assistant service.






Sarikaya & Schott         Expires 15 March 2026                 [Page 6]

Internet-Draft         AI/ML  Agents requirements         September 2025


   The network (e.g. in conjunction to IP Multimedia Subsystem, IMS)
   shall be able to support the interaction and collaboration between
   different user’s intelligent communication assistants, e.g. during an
   IMS calling service, both calling and callee parties are using
   intelligent communication services.

   The network (e.g. in conjunction to IMS) shall be able to support the
   intelligent communication assistant to use operator native
   capabilities (e.g. AR rendering, XR rendering in service hosting
   environment, SMS or voice).

3.  Implementation Issues

   In the section above Section 2 we described various kinds of AI
   agents 6G network needs.  In this section we will look at AI Agent
   implementation efforts so far.

   General purpose AI Agents like a travel AI Agent, loan handling,
   shopping for clothing AI agent are discussed in [aiprotocol].  These
   types of AI Agents can be built using Large Language Models, like GPT
   (Generative Pre-Trained Transformer)-4o, Gemini, Anthropic, etc.
   There are also open source ones like Llama.

   Like LLM tools, AI Agents work on prompt-completion mode, they get
   prompts and they reply with completions.  Designing AI Agents for
   specific tasks is developing to be an engineering practice.

   We will shortly describe the steps involved:

   Protocols involved include IP, TCP, UDP, QUIC for host communication,
   HTTP, SIP and RTP at the application layer.  Above all that are the
   protocols for AI Agents.  So far Model Context Protocol (MCP) [MCP]
   and Agent to Agent protocol [Agent2agent] which operate at the HTTP
   level and are expected to be standardized.

   AI Agent to API communication.  Agents provide services to user by
   invoking APIs either in the same domain or another domain.  AI Agent
   design includes to teach the agent what they are and give them enough
   information to know how to use them appropriately.

   User to AI Agent communication could be via various means like a
   phone call, a chat like by a chat app or via video.  Several types of
   media are involved simultaneously using protocols, tools established
   currently and widely used.







Sarikaya & Schott         Expires 15 March 2026                 [Page 7]

Internet-Draft         AI/ML  Agents requirements         September 2025


   AI Agent to user communication is similarly involving well
   established techniques like email, voice or chat when both the user
   and agent are on the same administrative domain.  If not,
   administrative configuration is required to allow the systems to
   communicate with each other using protocols like SIP.

   AI Agent implementation points to many areas in user to AI Agent, AI
   Agent to API and AI Agent to AI Agent where new protocol work is
   needed, these are discussed next.

3.1.  Future Work

   In AI Agent to API case, the discovery of APIs can happen using a
   well known URI and a link relation.  [RFC9727] defines the api-
   catalog well-known URI to which HTTPS GET request to the Publishers
   site returns an API catalog document.

   In the case of user to AI Agent, AI Agent discovery can be made using
   DNS [ajand].  For that purpose a DNS TXT record is specified.
   Providers advertise their agent service by publishing a single DNS
   TXT record at _agent.<domain> such as

   text _agent.example.com. 300 IN TXT
   "v=aid1;u=https://api.example.com/mcp;p=mcp;a=pat;s=Example AI Tools"

   which advertises a remote AI Agent called mcp.  Local agents can be
   advertised using Docker.

   Agents can be discovered using DNS lookups querying TXT records
   giving the domain name.  If the query succeeds and the protocol is
   supported the client can start using the AI Agent with the protocol.

   Authentication and authorization [RFC6749], [RFC6819] are to be
   discussed later.

4.  Security Considerations

   Security considerations of 6G AI Agents is TBD.

5.  IANA Considerations

   There are no IANA considerations for this document.

6.  Acknowledgements

7.  References

7.1.  Normative References



Sarikaya & Schott         Expires 15 March 2026                 [Page 8]

Internet-Draft         AI/ML  Agents requirements         September 2025


   [RFC6749]  Hardt, D., Ed., "The OAuth 2.0 Authorization Framework",
              RFC 6749, DOI 10.17487/RFC6749, October 2012,
              <https://www.rfc-editor.org/rfc/rfc6749>.

   [RFC6819]  Lodderstedt, T., Ed., McGloin, M., and P. Hunt, "OAuth 2.0
              Threat Model and Security Considerations", RFC 6819,
              DOI 10.17487/RFC6819, January 2013,
              <https://www.rfc-editor.org/rfc/rfc6819>.

   [RFC9727]  Smith, K., "api-catalog: A Well-Known URI and Link
              Relation to Help Discovery of APIs", RFC 9727,
              DOI 10.17487/RFC9727, June 2025,
              <https://www.rfc-editor.org/rfc/rfc9727>.

7.2.  Informative References

   [Agent2agent]
              Google, "Agent2Agent (A2A) Protocol", June 2025,
              <https://google.github.io/A2A/>.

   [aiagent6g]
              Yang, C., Huang,, H., Akhavain, A., Liu, F., An,, X.,
              Xing,, W., Li, J., Wang, A., and Y. Wencong,,
              "Requirements and Enabling Technologies of Agent Protocols
              for 6G Networks", Work in Progress, Internet-Draft, draft-
              hw-ai-agent-6g-00, 19 July 2025,
              <https://datatracker.ietf.org/doc/html/draft-hw-ai-agent-
              6g-00>.

   [aiagentusecase]
              Yu, M., Wang, A., Li, J., and Z. Li, "AI Agent Use Cases
              and Requirements in 6G Network", Work in Progress,
              Internet-Draft, draft-yu-ai-agent-use-cases-in-6g-01, 7
              July 2025, <https://datatracker.ietf.org/doc/html/draft-
              yu-ai-agent-use-cases-in-6g-01>.

   [aiprotocol]
              Rosenberg, J. and C. F. Jennings, "Framework, Use Cases
              and Requirements for AI Agent Protocols", Work in
              Progress, Internet-Draft, draft-rosenberg-ai-protocols-00,
              5 May 2025, <https://datatracker.ietf.org/doc/html/draft-
              rosenberg-ai-protocols-00>.

   [ajand]    Agent Community, "Agent Identity and Discovery (AID)",
              August 2025, <https://docs.agentcommunity.org/aid/>.

   [LLMPaper] al., A. V. et., "Attention is all you need", August 2017,
              <https://arxiv.org/html/1706.03762v7>.



Sarikaya & Schott         Expires 15 March 2026                 [Page 9]

Internet-Draft         AI/ML  Agents requirements         September 2025


   [MCP]      Anthropic, "Model Context Protocol", June 2025,
              <https://modelcontextprotocol.io/>.

   [TR22.870] 3rd Generation Partnership Project, "Study on 6G Use Cases
              and Service Requirements", June 2025,
              <https://www.3gpp.org/ftp/Specs/
              archive/22_series/22.870/22870-031.zip>.

   [TS22.261] 3rd Generation Partnership Project, "Service Requirements
              for the 5G System", December 2024.

Authors' Addresses

   Behcet Sarikaya
   Unaffiliated
   Email: sarikaya@ieee.org


   Roland Schott
   Deutsche Telekom
   Deutsche-Telekom-Allee 9
   64295 Darmstadt
   Germany
   Email: Roland.Schott@telekom.de



























Sarikaya & Schott         Expires 15 March 2026                [Page 10]
