Internet Research Task Force J. Jeong, Ed. Internet-Draft M. Gu Intended status: Informational Y. Ahn Expires: 20 May 2027 Sungkyunkwan University J. Park ETRI B. An KETI 16 November 2026 An Agentic AI Framework for the Management of Networks, Security, and AI Services draft-jeong-nmrg-agentic-ai-framework-01 Abstract This document specifies an agentic AI framework for the management of networks, security, and AI services. This framework is an Intent- Based System (IBS) to enforce a human-language intent at a target network with the translated policy for networks, security, or AI services. It consists of a User System, a Cloud System, an Edge System, and a Device. Target devices in this framework include Network Forwarding Elements (e.g., router and switch), Network Security Functions (e.g., firewall, web filter, and DDoS-attack mitigator), Internet-of-Things (IoT) Devices, Physical AI Robots, Software-Defined Vehicles (SDV), Unmanned Aerial Vehicles (UAV), and Urban Air Mobility (UAM). This document describes the agentic AI framework with its components and interfaces where the components include AI agents and supporting knowledge repositories (i.e., knowledge base), and also inter-agent interfaces use the Agent-to- Agent (A2A) protocol. 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." Jeong, et al. Expires 20 May 2027 [Page 1] Internet-Draft Agentic AI Framework November 2026 This Internet-Draft will expire on 20 May 2027. Copyright Notice Copyright (c) 2026 IETF Trust and the persons identified as the document authors. All rights reserved. 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. Terminology . . . . . . . . . . . . . . . . . . . . . . . . . 3 3. Agentic AI Framework for Service Management . . . . . . . . . 5 4. Interfaces in Agentic AI Framework . . . . . . . . . . . . . 9 5. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 10 6. Security Considerations . . . . . . . . . . . . . . . . . . . 10 7. References . . . . . . . . . . . . . . . . . . . . . . . . . 10 7.1. Normative References . . . . . . . . . . . . . . . . . . 10 7.2. Informative References . . . . . . . . . . . . . . . . . 11 Appendix A. Changes from draft-jeong-nmrg-agentic-ai-framework-00 . . . . . . . . 15 Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . . . 16 Contributors . . . . . . . . . . . . . . . . . . . . . . . . . . 16 Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 17 1. Introduction Agentic AI opens a new door providing human users with human-friendly services through Large Language Models (LLMs) such as GPT-3 [GPT-3] and Flan-T5 [Flan-T5]. Also, network softwarization has been widely adopted in various domains such as data centers and mobile networks [TS-23.501]. The network softwarization is realized with Network Functions Virtualization (NFV) [ETSI-NFV][ETSI-NFV-Release-2] and Software-Defined Networking (SDN) [RFC7149]. Furthermore, Intent- Based Networking (IBN) [RFC9315][Survey-IBN-CST-2023][ClickINC] can support human-friendly configuration for target networks and security systems. Jeong, et al. Expires 20 May 2027 [Page 2] Internet-Draft Agentic AI Framework November 2026 This document specifies an agentic AI framework for the management of networks, security, and AI services. This framework is an Intent- Based System (IBS) including the IBN that enforces a human-language intent at a target network. It aims at the IBS in data centers, corporate networks, campus networks, and home networks rather than public networks like the Internet. The agentic AI framework in this document supports the translation of a human-language intent and the enforcement of the corresponding service(s) through multiple AI agents in target networks. This intent can be translated into a specific policy for networks, security, or AI services. The agentic AI framework in this document consists of a User System, a Cloud System, an Edge System, and a Device. Devices under the control of this framework include Network Forwarding Elements (e.g., router and switch), Network Security Functions (e.g., firewall, web filter, and DDoS-attack mitigator), Internet-of-Things (IoT) Devices, Physical AI Robots, Software- Defined Vehicles (SDV) [AUTOSAR-SDV][Eclipse-SDV][COVESA], Unmanned Aerial Vehicles (UAV), and Urban Air Mobility (UAM). Thus, this document describes the agentic AI framework with its components and interfaces where the components are AI agents and the interfaces use the Agent-to-Agent (A2A) protocol [A2A][A2A-Specification]. 2. Terminology This document uses the terminology described in [RFC9315] and [I-D.irtf-nmrg-ibn-usecases]. The new terms are defined below: * AI Agent: A software module that can translate a human-language intent into a structured policy in a Domain-Specific Language (DSL). An AI agent can communicate with another AI agent for collaboration via the Agent-to-Agent (A2A) protocol. It can use available computing, storage, and network resources via Model Context Protocol (MCP) [MCP][MCP-Specification]. The MCP accesses data and file systems, development tools, productivity tools, and physical AI tools for the requested service. Jeong, et al. Expires 20 May 2027 [Page 3] Internet-Draft Agentic AI Framework November 2026 * Agent Catalog: A logical collection of Agent Cards [A2A-Specification], or references to them, describing AI agents known to the framework. It supports the lookup of candidate AI agents based on their advertised skills and interaction requirements. In this document, the Agent Catalog constitutes the agent-metadata part of the Knowledge Base that is a database for intent translation. Entries in the Agent Catalog may be populated and refreshed through discovery or registration mechanisms. A storage representation format (e.g., XML [W3C.REC-xml-20081126], JSON [RFC8259], or YAML [YAML]), access information (e.g., IP address and port number), and an access mechanism may be included in the Agent Catalog. * Intent: A set of operational goals (i.e., what a network should meet) and outcomes (i.e., what the network is supposed to deliver) defined in a declarative manner without specifying how they are achieved or should be implemented [RFC9315]. * Intent-Based System (IBS): A system that enforces an intent from a user (or administrator) into a target system (e.g., router, switch, firewall, web filter, IoT device, robot, and SDV) through an intent life cycle [RFC9315]. * Intent Translator: A component that can translate an intent in a natural language (e.g., English) into a specific intent (i.e., a refined intent) or the corresponding high-level policy (i.e., a network policy, security policy, or AI service policy) using Natural Language Processing (NLP) and Large Language Models (LLMs) [Flan-T5][GPT-3] [USENIX-ATC-Lumi][BERT]. That is, an Intent Translator converts a natural-language intent into a structured policy representation (i.e., a specific intent or a high-level policy) based on [I-D.gu-nmrg-intent-translator]. A specific intent denotes a refined, structured representation of a goal assigned to a supervised agent (e.g., Edge Agent or Worker Agent) or a high-level policy with concrete rules. It also selects at least one supervised agent to enforce the specific intent or the high-level policy. * Knowledge Base (KB): A logical repository that provides domain- specific policy knowledge and agent metadata used by the framework. Policy knowledge includes target schemas, valid policy examples, and semantic constraints, drawing on the Policy Knowledge Base concept described in [I-D.gu-nmrg-intent-translator]. In this document, agent metadata is organized as an Agent Catalog. Policy knowledge and agent metadata are distinct logical categories and may reside in separate physical repositories. A graph-based representation is an implementation option. Jeong, et al. Expires 20 May 2027 [Page 4] Internet-Draft Agentic AI Framework November 2026 * Orchestrator: A component that governs and monitors supervised agents (e.g., Edge Agent and Worker Agent) to achieve the fulfillment and assurance of the target intent [RFC9315]. Through the monitoring of the supervised agents by the Orchestrator, the activities and performance of those agents are monitored and analyzed. If needed, the specific intent is augmented by the Orchestrator. Also, in some cases, a new specific intent may be generated by the Orchestrator and be delivered to an appropriate target agent for reconfiguration. * Physical AI Object (PAO): A physical object that can move with an AI agent, power source, and wireless communication capability (e.g., 5G Vehicle-to-Everything (V2X)). A PAO can be an intelligent Internet-of-Things (IoT) Device, Software-Defined Vehicle (SDV) [AUTOSAR-SDV][Eclipse-SDV][COVESA], Unmanned Aerial Vehicle (UAV), or Urban Air Mobility (UAM). * Virtual AI Object (VAO): A virtual object that can handle network and security services with an AI agent and wired/wireless communication capability (e.g., Gigabit Ethernet, Wi-Fi, and 5G V2X). A VAO can be either an SDN Controller [RFC7149] for network management or a Security Controller [I-D.ietf-i2nsf-applicability] for security management. 3. Agentic AI Framework for Service Management This section specifies an Agentic AI System for AI Service Management in target domains, as shown in Figure 1. In this figure, a human user (e.g., network administrator, building manager, and home user) uses a User System (e.g., smartphone and computer) for managing networks, security, and AI services. The User System interacts with a Cloud System or an Edge System for the human user's intents. A Cloud System manages multiple Edge Systems for the sake of human users. An Edge System manages multiple Devices for networks, security, and AI services like in Figure 1. The devices can be either Virtual AI Objects (VAOs) or Physical AI Objects (PAOs) having at least one Worker AI Agent for the interaction with an Edge Agent and other Worker AI Agents. Jeong, et al. Expires 20 May 2027 [Page 5] Internet-Draft Agentic AI Framework November 2026 User System +------------+ | User Agent | +------------+ ^ ^ | A2A | A2A | v Edge System v Cloud System ****************************************** ********** * * * * * * * +----------+ * * +-----------------+ * * | Cloud | * * | Edge Agent | *<->* | Agent | * * +--------^--------+ *A2A* +----------+ * * | * * * * v * * * ****************************************** ********** ^ ^ ^ | A2A | A2A | A2A v v v +----------------+ +----------------+ +----------------+ | +------+ | | +------+ | | +------+ | | |Worker| | | |Worker| | | |Worker| | | |Agent1| |<-->| |Agent2| |<-->| |Agent3| | | +---^--+ |A2A | +---^--+ |A2A | +---^--+ | | | MCP | | | MCP | | | MCP | | +--v----+ | | +--v----+ | | +--v----+ | | |Modules| | | |Modules| | | |Modules| | | +-------+ | | +-------+ | | +-------+ | +----------------+ +----------------+ +----------------+ Device1 Device2 Device3 <----> Wired/Wireless Link Figure 1: Agentic AI System for Network, Security, and AI Service Management Figure 2 shows an Agentic AI Framework for the management of networks, security, and AI services. A User Agent in the User System generates an intent for the human user's service demand and sends it to either a Cloud System or an Edge System. Either a Cloud Agent in the Cloud System or an Edge Agent in the Edge System receives the intent from the User Agent. In the case where the Cloud Agent receives an intent from the User Agent, the Cloud Agent translates the intent into the corresponding high-level policy through its Intent Translator. For the authentication and authorization of a User Agent, the User Agent in Jeong, et al. Expires 20 May 2027 [Page 6] Internet-Draft Agentic AI Framework November 2026 the User System needs to contact the Cloud Agent in the Cloud System. This security process is necessary for the management of networks, security, and AI services at the target domains where the User Agent has access permission. This is different from the assumption that an AI agent can discover other AI agents to help its task like travel agents to reserve airplane tickets, hotel rooms, and local transportation tickets. +----------------------+ | User Agent | |(Smartphone, Computer)| +----------------------+ ^ | ^ | | Intent | Report | v | | +----------------------------------------------------------------+ | | +-------------------+ Agent Information +--------------------+ | | | | Cloud Agent |<----------------->| Knowledge Base | | | | |(Intent Translator,| |(Edge Agent Catalog)| | | | | Orchestrator) | | | | | | +-------------------+ +--------------------+ | | +----------------------------------------------------------------+ | ^ ^ | Intent | Intent (Report, Monitoring Data) | Agent Card |(Report) | | v v v +------------------------------------------------------------------+ | +-------------------+ +----------------------+ | | | Edge Agent | Agent Information | Knowledge Base | | | |(Intent Translator,|<----------------->|(Worker Agent Catalog)| | | | Orchestrator) | | | | | +-------------------+ +----------------------+ | +------------------------------------------------------------------+ ^ ^ | Intent (Report, Monitoring Data) | Agent Card | | v v +---------------------------------------------------------------------+ | | | +------------------+ +----------------------+ +-----------------+ | | | Worker Agent1: | | Worker Agent2: | | Worker Agent3: | | | | SDN Controller | | Security Controller | | Physical AI | | | | (Router, Switch) | |(Firewall, Web Filter)| |(Robot, SDV, IoT)| | | +------------------+ +----------------------+ +-----------------+ | +---------------------------------------------------------------------+ Jeong, et al. Expires 20 May 2027 [Page 7] Internet-Draft Agentic AI Framework November 2026 Figure 2: Agentic AI Framework for Network, Security, and AI Service Management Each Cloud Agent or Edge Agent accesses its Knowledge Base through a repository access interface. Its Intent Translator retrieves domain- specific schemas and semantic constraints from the policy-knowledge part of the Knowledge Base to support policy generation and validation. There exists an Agent Catalog that is a collection of Agent Cards [A2A-Specification] used for searching for candidate agents to perform the intent. There are two kinds of Agent Catalogs, namely an Edge Agent Catalog and a Worker Agent Catalog. The Edge Agent Catalog contains the Agent Cards of Edge Agents inside Edge Systems. On the other hand, the Worder Agent Catalog contains the Agent Cards of Workder Agents inside Devices. The Knowledge Base supplies information for intent translation and enforcement such as intent translation, policy validation, and agent selection. Note that the agent discovery for an Agent Catalog can be performed in the following two approaches. The first approach is a reactive way using an agent discovery protocol (e.g., DNS and mDNS) [I-D.seethiraju-dawn-dan][I-D.zhang-dawn-agent-discovery-framework]. The second approach is a proactive way (e.g., a capability registration protocol) [I-D.ietf-i2nsf-capability-data-model][I-D.ietf-i2nsf-registration-interface-dm][I-D.ietf-i2nsf-applicability]. The Agentic AI Framework in this document can accommodate these two kinds of agent discovery approaches. A policy-knowledge role is used to translate an intent into a specific intent (i.e., a refined intent) with the Policy Knowledge Base in [I-D.gu-nmrg-intent-translator]. Policy schemas and semantic constraints are supplied for each supported domain. For policy generation, a schema (i.e., a data model) with constraints for the service management needs to be developed. Note that a policy based on such a scheme can be expressed in XML [W3C.REC-xml-20081126], JSON [RFC8259], or YAML [YAML]. Once the User Agent is authenticated and authorized through the Cloud Agent, the User Agent can directly interact with an Edge Agent in an Edge System that can handle the User Agent's intent with its Work Agents, as shown in Figure 2. When the Edge Agent receives a specific intent (i.e., a refined intent) from the Cloud Agent, it refines that intent into another specific intent or a high-level policy for Worker Agents. When it receives a natural-language intent directly from the User Agent, its Intent Translator first generates a structured high-level policy, which is then refined in the same way. Each specific intent represents a worker-specific goal or policy in an XML, JSON, or YAML Jeong, et al. Expires 20 May 2027 [Page 8] Internet-Draft Agentic AI Framework November 2026 document according to its target model. Within this framework, the Intent Translator queries the Agent Catalog to obtain candidate Agent Cards and evaluates their suitability for the requested task. Policy refinement and Worker Agent selection are extensions introduced by this document. Refinement preserves the goals and constraints of the original intent. The Edge Agent sends the specific intent or the high-level policy to the selected Worker Agent(s) to enforce the requested service corresponding to the intent from the User Agent. When a Worker Agent receives a specific intent or a high-level policy, it performs the requested service using its internal resources and external resources via MCP [MCP-Specification] with predefined APIs. Operation results for the given intent are delivered as a report (e.g., success or failure) or monitoring data (e.g., alarms, events, logs, or counters) [I-D.ietf-i2nsf-nsf-monitoring-data-model] from a supervised source component (e.g., Worker Agent, Edge Agent, and Cloud Agent) to a supervising destination component (e.g., Edge Agent, Cloud Agent, and User Agent) in the Agentic AI Framework in Figure 2. When a Cloud Agent receives a report or monitoring data from an Edge Agent, the Orchestrator in the Cloud Agent checks the report or monitoring data to determine an appropriate action, depending on the message in the report or the monitoring data. Also, when an Edge Agent receives a report or monitoring data from a Worker Agent, the Orchestrator in the Edge Agent handles the report or monitoring data in the same way as the Cloud Agent. Therefore, the operation results (i.e., reports and monitoring data) can be used as feedback for fulfilling and assuring the intent through the closed- loop control in the Agentic AI Framework [I-D.irtf-nmrg-ibn-usecases]. 4. Interfaces in Agentic AI Framework Interfaces in the Agentic AI Framework use A2A [A2A-Specification] and MCP [MCP-Specification]. The interfaces among the User Agent, the Cloud Agent, the Edge Agent, and the Worker Agents use A2A, as shown in Figure 1. The message formats used by A2A conform to the specification of A2A [A2A-Specification]. The interfaces among agents and modules in each system (e.g., User Agent, Cloud Agent, Edge Agent, and Worker Agent) use MCP, as shown in Figure 1. The message formats used by MCP conform to the specification of MCP [MCP-Specification]. Jeong, et al. Expires 20 May 2027 [Page 9] Internet-Draft Agentic AI Framework November 2026 5. IANA Considerations This document does not require any IANA actions. 6. Security Considerations Authentication and authorization mechanisms should be used to check the validity of User Agents. For trustworthy cooperation, mutual authentication should be performed beforehand among the Cloud Agent, the Edge Agents, and Worker Agents. An intent from a User Agent should be evaluated by either the Cloud Agent or the Edge Agent to determine whether it is harmless to the Agentic AI Framework or not. If the intent is harmful, either the Cloud Agent or the Edge Agent should log this intent and report the harmfulness of the intent to the User Agent which issued the intent. For reliable and agile AI services, the Agentic AI Framework should perform governance by monitoring and auditing the activities of AI agents including the User Agent, Cloud Agent, Edge Agents, and Worker Agents. Such an auditing system may operate as an independent entity in the Agentic AI Framework so that it can audit the AI agents without any bias. 7. References 7.1. Normative References [RFC6020] Bjorklund, M., Ed., "YANG - A Data Modeling Language for the Network Configuration Protocol (NETCONF)", RFC 6020, DOI 10.17487/RFC6020, October 2010, . [RFC6241] Enns, R., Ed., Bjorklund, M., Ed., Schoenwaelder, J., Ed., and A. Bierman, Ed., "Network Configuration Protocol (NETCONF)", RFC 6241, DOI 10.17487/RFC6241, June 2011, . [RFC7149] Boucadair, M. and C. Jacquenet, "Software-Defined Networking: A Perspective from within a Service Provider Environment", RFC 7149, DOI 10.17487/RFC7149, March 2014, . [RFC7950] Bjorklund, M., Ed., "The YANG 1.1 Data Modeling Language", RFC 7950, DOI 10.17487/RFC7950, August 2016, . Jeong, et al. Expires 20 May 2027 [Page 10] Internet-Draft Agentic AI Framework November 2026 [RFC8040] Bierman, A., Bjorklund, M., and K. Watsen, "RESTCONF Protocol", RFC 8040, DOI 10.17487/RFC8040, January 2017, . [RFC8259] Bray, T., Ed., "The JavaScript Object Notation (JSON) Data Interchange Format", STD 90, RFC 8259, DOI 10.17487/RFC8259, December 2017, . [RFC8329] Lopez, D., Lopez, E., Dunbar, L., Strassner, J., and R. Kumar, "Framework for Interface to Network Security Functions", RFC 8329, DOI 10.17487/RFC8329, February 2018, . [RFC9315] Clemm, A., Ciavaglia, L., Granville, L. Z., and J. Tantsura, "Intent-Based Networking - Concepts and Definitions", RFC 9315, DOI 10.17487/RFC9315, October 2022, . [RFC9365] Jeong, J., Ed., "IPv6 Wireless Access in Vehicular Environments (IPWAVE): Problem Statement and Use Cases", RFC 9365, DOI 10.17487/RFC9365, March 2023, . 7.2. Informative References [I-D.irtf-nmrg-ibn-usecases] Yao, K., Chen, D., Jeong, J. P., Wu, Q., Yang, C., Contreras, L. M., and G. Fioccola, "Use Cases and Practices for Intent-Based Networking", Work in Progress, Internet-Draft, draft-irtf-nmrg-ibn-usecases-05, 2 November 2026, . [I-D.gu-nmrg-intent-translator] Gu, M., Jeong, J. P., and K. Shim, "An Agentic AI Framework for Hallucination Mitigation in Network Intent Translation", Work in Progress, Internet-Draft, draft-gu- nmrg-intent-translator-05, 15 November 2026, . Jeong, et al. Expires 20 May 2027 [Page 11] Internet-Draft Agentic AI Framework November 2026 [I-D.seethiraju-dawn-dan] Seethiraju, R. R., Thakar, S., Shyamsunder, K., and E. Osterweil, "DNS-Based Agent Naming (DAN): AIDISCA and AIINDEX Resource Records for AI Agent Discovery", Work in Progress, Internet-Draft, draft-seethiraju-dawn-dan-01, 30 October 2026, . [I-D.zhang-dawn-agent-discovery-framework] Zhang, B., Dunbar, L., and Y. Yang, "A Framework for Agent Discovery in DAWN", Work in Progress, Internet-Draft, draft-zhang-dawn-agent-discovery-framework-09, 20 October 2026, . [I-D.ietf-i2nsf-capability-data-model] Hares, S., Jeong, J. P., Kim, J. T., Moskowitz, R., and Q. Lin, "I2NSF Capability YANG Data Model", Work in Progress, Internet-Draft, draft-ietf-i2nsf-capability-data-model-32, 23 May 2022, . [I-D.ietf-i2nsf-registration-interface-dm] Hyun, S., Jeong, J. P., Roh, T., Wi, S., and J. Jung-Soo, "I2NSF Registration Interface YANG Data Model for NSF Capability Registration", Work in Progress, Internet- Draft, draft-ietf-i2nsf-registration-interface-dm-26, 10 May 2023, . [I-D.ietf-i2nsf-nsf-monitoring-data-model] Jeong, J. P., Lingga, P., Hares, S., Xia, L., and H. Birkholz, "I2NSF NSF Monitoring Interface YANG Data Model", Work in Progress, Internet-Draft, draft-ietf- i2nsf-nsf-monitoring-data-model-20, 1 June 2022, . [I-D.ietf-i2nsf-applicability] Jeong, J. P., Hyun, S., Ahn, T., Hares, S., and D. Lopez, "Applicability of Interfaces to Network Security Functions to Network-Based Security Services", Work in Progress, Internet-Draft, draft-ietf-i2nsf-applicability-19, 3 April 2025, . Jeong, et al. Expires 20 May 2027 [Page 12] Internet-Draft Agentic AI Framework November 2026 [W3C.REC-xml-20081126] Bray, T., Ed., Paoli, J., Ed., Sperberg-McQueen, C.M., Ed., Maler, E., Ed., and F. Yergeau, Ed., "Extensible Markup Language (XML) 1.0 (Fifth Edition)", W3C Recommendation, 26 November 2008, . [YAML] Ingerson, B., Evans, C., and O. Ben-Kiki, "Yet Another Markup Language (YAML) 1.0", Available: https://yaml.org/spec/history/2001-05-26.html, October 2023. [TS-23.501] "System Architecture for the 5G System (5GS)", Available: https://portal.3gpp.org/desktopmodules/Specifications/ SpecificationDetails.aspx?specificationId=3144, September 2023. [TS-28.312] "Intent Driven Management Services for Mobile Networks", Available: https://portal.3gpp.org/desktopmodules/Specifications/ SpecificationDetails.aspx?specificationId=3554, September 2023. [TR-28.812] "Study on Scenarios for Intent Driven Management Services for Mobile Networks", Available: https://portal.3gpp.org/desktopmodules/Specifications/ SpecificationDetails.aspx?specificationId=3553, December 2020. [TS-23.288] "Architecture Enhancements for 5G System (5GS) to Support Network Data Analytics Services", Available: https://portal.3gpp.org/desktopmodules/Specifications/ SpecificationDetails.aspx?specificationId=3579, September 2023. [TS-29.520] "Network Data Analytics Services", Available: https://portal.3gpp.org/desktopmodules/Specifications/ SpecificationDetails.aspx?specificationId=3355, September 2023. Jeong, et al. Expires 20 May 2027 [Page 13] Internet-Draft Agentic AI Framework November 2026 [ETSI-NFV] "Network Functions Virtualisation (NFV); Architectural Framework", Available: https://www.etsi.org/deliver/etsi_gs/ nfv/001_099/002/01.02.01_60/gs_nfv002v010201p.pdf, December 2014. [ETSI-NFV-Release-2] "Network Functions Virtualisation (NFV) Release 2; Management and Orchestration; Architectural Framework Specification", Available: https://www.etsi.org/deliver/etsi_gs/ nfv/001_099/006/02.01.01_60/gs_nfv006v020101p.pdf, January 2021. [REST] Fielding, R. and R. Taylor, "Principled Design of the Modern Web Architecture", ACM Transactions on Internet Technology, Vol. 2, Issue 2, Available: https://dl.acm.org/doi/10.1145/514183.514185, May 2002. [GPT-3] Brown, T., "Language Models are Few-Shot Learners", arXiv:2005.14165, Available: https://arxiv.org/abs/2005.14165, May 2020. [Flan-T5] Chung, H., "Scaling Instruction-Finetuned Language Models", arXiv:2210.11416, Available: https://arxiv.org/abs/2210.11416, October 2022. [USENIX-ATC-Lumi] Jacobs, A., Pfitscher, R., Ribeiro, R., Ferreira, R., Granville, L., Willinger, W., and S. Rao, "Hey, Lumi! Using Natural Language for Intent-Based Network Management", USENIX Annual Technical Conference, Available: https://www.usenix.org/conference/atc21/presentation/ jacobs, July 2021. [BERT] Devlin, J., Chang, M., Lee, K., and K. Toutanova, "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding", NAACL-HLT Conference, Available: https://aclanthology.org/N19-1423.pdf, June 2019. [AUTOSAR-SDV] "AUTOSAR Adaptive Platform", Available: https://www.autosar.org/standards/adaptive-platform, March 2024. Jeong, et al. Expires 20 May 2027 [Page 14] Internet-Draft Agentic AI Framework November 2026 [Eclipse-SDV] "Eclipse Software Defined Vehicle Working Group Charter", Available: https://www.eclipse.org/org/workinggroups/sdv- charter.php, March 2024. [COVESA] "Connected Vehicle Systems Alliance", Available: https://covesa.global/, March 2024. [A2A] "Agent2Agent (A2A) Protocol", Available: https://a2a- protocol.org/, November 2026. [A2A-Specification] "Agent2Agent (A2A) Protocol Specification", Available: https://a2a-protocol.org/latest/specification/, November 2026. [MCP] "Model Context Protocol (MCP)", Available: https://modelcontextprotocol.io/, November 2026. [MCP-Specification] "Model Context Protocol Specification", Available: https://modelcontextprotocol.info/specification/, November 2026. [Kubernetes] "Kubernetes: Cloud Native Computing Platform", Available: https://kubernetes.io/, March 2024. [Survey-IBN-CST-2023] Leivadeas, A. and M. Falkner, "A Survey on Intent-Based Networking", Available: https://ieeexplore.ieee.org/document/9925251, March 2023. [ClickINC] Xu, W., Zhang, Z., Feng, Y., Song, H., Chen, Z., Wu, W., Liu, G., Zhang, Y., Liu, S., Tian, Z., and B. Liu, "ClickINC: In-network Computing as a Service in Heterogeneous Programmable Data-center Networks", Publisher: ACM SIGCOMM, Available: https://dl.acm.org/doi/10.1145/3603269.3604835, September 2023. Appendix A. Changes from draft-jeong-nmrg-agentic-ai-framework-00 The following changes are made from draft-jeong-nmrg-agentic-ai- framework-00: Jeong, et al. Expires 20 May 2027 [Page 15] Internet-Draft Agentic AI Framework November 2026 * This version has corrected the Agentic AI System in Figure 1 with Wired/Wireless Link. * This version has clarified the Agentic AI Framework in Figure 2 with detailed descriptions on the framework's components and procedures. Acknowledgments This document is a product of the NMRG including the RG Chairs (Jerome Francois and Jeferson Campos Nobre). This document benefitted from the review and comments from the following people: Yong-Geun Hong and Joo-Sang Youn. The authors sincerely appreciate their efforts and kind help. This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea Ministry of Science and ICT (MSIT) (No. RS- 2024-00398199). Contributors The following are coauthors of this document: Jisuk Chae Department of Computer Science & Engineering Sungkyunkwan University 2066 Seobu-Ro, Jangan-Gu Suwon Gyeonggi-Do 16419 Republic of Korea Phone: +82 31 299 4106 Email: sue030124@skku.edu URI: http://iotlab.skku.edu/people-Jisuk-Chae.php Eunjin Hwang Department of Computer Science & Engineering Sungkyunkwan University 2066 Seobu-Ro, Jangan-Gu Suwon Gyeonggi-Do 16419 Republic of Korea Phone: +82 31 299 4106 Email: eunijhwang@skku.edu URI: https://iotlab.skku.edu/people-Eunjin-Hwang.php Jeong, et al. Expires 20 May 2027 [Page 16] Internet-Draft Agentic AI Framework November 2026 KiHyun Shim Department of Computer Science & Engineering Sungkyunkwan University 2066 Seobu-Ro, Jangan-Gu Suwon Gyeonggi-Do 16419 Republic of Korea Phone: +82 31 299 4106 Email: tlarlguswh@skku.edu URI: https://iotlab.skku.edu/people-KiHyun_Shim.php Authors' Addresses Jaehoon Paul Jeong (editor) Department of Computer Science & Engineering Sungkyunkwan University 2066 Seobu-Ro, Jangan-Gu Suwon Gyeonggi-Do 16419 Republic of Korea Phone: +82 31 299 4957 Email: pauljeong@skku.edu URI: http://iotlab.skku.edu/people-jaehoon-jeong.php Mose Gu Department of Computer Science & Engineering Sungkyunkwan University 2066 Seobu-Ro, Jangan-Gu Suwon Gyeonggi-Do 16419 Republic of Korea Phone: +82 31 299 4106 Email: rna0415@skku.edu URI: http://iotlab.skku.edu/people-Moses-Gu.php Jeong, et al. Expires 20 May 2027 [Page 17] Internet-Draft Agentic AI Framework November 2026 Yoseop Ahn Department of Computer Science & Engineering Sungkyunkwan University 2066 Seobu-Ro, Jangan-Gu Suwon Gyeonggi-Do 16419 Republic of Korea Phone: +82 31 299 4106 Email: ahnjs124@skku.edu URI: http://iotlab.skku.edu/people-Ahn-Yoseop.php Jung-Soo Park Electronics and Telecommunications Research Institute 218 Gajeong-Ro, Yuseong-Gu Daejeon 34129 Republic of Korea Phone: +82 42 860 6514 Email: pjs@etri.re.kr Byoungman Robert An Intelligent Information R&D Division Korea Electronics Technology Institute Global R and D Center 6th floor #22, Daewangpangyo-ro 712beon-gil Seongnam Gyeonggi-Do 13488 Republic of Korea Phone: +82 31 739 7463 Email: bman@keti.re.kr URI: https://www.keti.re.kr/eng/main/main.php Jeong, et al. Expires 20 May 2027 [Page 18]