Internet Research Task Force B. An, Ed. Internet-Draft KETI Intended status: Informational J. Jeong, Ed. Expires: 6 May 2027 Sungkyunkwan University P. Park S. Jang KETI 2 November 2026 An Agentic AI Framework for Software-Defined Vehicles in Cooperative Intelligent Transportation Systems draft-an-nmrg-i2icf-cits-03 Abstract This document specifies an Agentic AI Framework for orchestrating, managing, and monitoring AI Computing Functions (ACFs) for Software- Defined Vehicles (SDVs) in Cooperative Intelligent Transportation Systems (C-ITS). AI agents as ACFs communicate with each other via the Agent-to-Agent (A2A) protocol. SDVs decouple vehicular functions from underlying hardware and expose them as software-driven, continuously updatable services; this architectural shift makes them natural participants in an agentic control plane that spans vehicles, roadside infrastructure, and mobile networks. AI agents are co- located with each functional entity of the C-ITS architecture (e.g., C-ITS Center, Government Public Center, C-ITS Infra, Mobile Network Operator (MNO), Roadside Unit (RSU), SDV, and Vulnerable Road User (VRU)) and interact over an A2A protocol overlay to advertise capabilities, discover peers, negotiate resources, and coordinate the placement and execution of ACFs across multi-domain networks. In the context of Vehicle-to-Everything (V2X) communications, this agentic overlay enables efficient management of Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communications and their integration with C-ITS by leveraging in-network computing to optimize real-time communication, streamline traffic management, and enhance data processing and security services at the network edge. The proposed framework aligns with the up-to-date agentic AI and A2A applicability to network management, and adapts these concepts to the specific operational and safety requirements of SDV-centric C-ITS deployments. Requirements Language The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in RFC 2119 [RFC2119]. An, et al. Expires 6 May 2027 [Page 1] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 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 6 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 . . . . . . . . . . . . . . . . . . . . . . . . 3 2. Agentic AI Framework and Interfaces for SDV in C-ITS . . . . 5 2.1. Agentic AI Framework for SDV, C-ITS, and MNO Networking . . . . . . . . . . . . . . . . . . . . . . . 5 2.2. Agentic AI Interfaces . . . . . . . . . . . . . . . . . . 11 3. Use Cases for Agentic AI in SDV and C-ITS . . . . . . . . . . 12 4. A2A Use Cases for SDV-Centric C-ITS Integration . . . . . . . 14 5. Agent Cards for SDVs and C-ITS Entities . . . . . . . . . . . 17 6. YANG-based Structured Data for A2A Communication in SDV and C-ITS . . . . . . . . . . . . . . . . . . . . . . . . . . 19 7. Operational Considerations . . . . . . . . . . . . . . . . . 30 7.1. Agent Skills as Expertise Expansion . . . . . . . . . . . 30 7.2. Knowledge Base as Ground Truth Data . . . . . . . . . . . 31 7.3. Event-driven A2A for Safety Signalling . . . . . . . . . 31 7.4. Scalability . . . . . . . . . . . . . . . . . . . . . . . 31 An, et al. Expires 6 May 2027 [Page 2] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 7.5. Latency and Performance Constraints . . . . . . . . . . . 31 7.6. Reliability and Failure Handling . . . . . . . . . . . . 32 7.7. Agent Lifecycle and Resource Management . . . . . . . . . 33 7.8. Inter-Domain Operational Challenges . . . . . . . . . . . 33 8. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 33 9. Security Considerations . . . . . . . . . . . . . . . . . . . 33 10. References . . . . . . . . . . . . . . . . . . . . . . . . . 34 10.1. Normative References . . . . . . . . . . . . . . . . . . 34 10.2. Informative References . . . . . . . . . . . . . . . . . 35 Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . . . 37 Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 37 1. Introduction This document proposes an Agentic AI framework for coordinating AI Computing Functions (ACFs) across Software-Defined Vehicles (SDVs), roadside infrastructure, and mobile networks in Cooperative Intelligent Transportation Systems (C-ITS). An ACF is a processing function that uses AI techniques, for example perception inference, sensor fusion using an AI model, or traffic prediction. An AI agent is the entity that interprets an intent, selects and coordinates functions or tools, and monitors the resulting task. An agent and an ACF are therefore distinct roles. In-network and edge computing provide relevant deployment and resource-management foundations. Prior work describes use cases for In-network Computing Functions called ACFs [I-D.jeong-nmrg-agentic-ai-framework][I-D.yao-tsvwg-cco-problem-statement-and-usecases][I-D.irtf-coinrg-use-cases]. However, computation inside a network is not necessarily AI computation. Message forwarding, deterministic aggregation, network- slice configuration, and key rotation can remain conventional supporting services or tools invoked by an agent. This document does not classify them as ACFs solely because they participate in an agentic workflow. The proposed framework addresses registration, configuration, orchestration, and monitoring of ACFs and their supporting services across vehicles and infrastructure. The Interface to Network Security Functions (I2NSF) framework [RFC8329] provides relevant management concepts for Network Security Functions (NSFs), but an AI agent's coordination role is distinct from the function that it invokes. The following architecture applies agent-to-agent coordination to C-ITS and MNO integration. The use cases describe intended behaviors, not measured performance or deployment results. A distinguishing focus of this document is the Software-Defined Vehicle (SDV) as the primary endpoint of the Agentic AI framework. In an SDV, traditionally hardware-bound vehicular functions (e.g., An, et al. Expires 6 May 2027 [Page 3] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 perception, planning, control, infotainment, and diagnostics) are realized as software components running on a consolidated, zonal compute platform and are continuously updated over the air. This software-defined nature aligns naturally with the agentic AI model: each SDV can host one or more AI agents that expose vehicle capabilities (e.g., compute, sensing, connectivity, and safety classes) as A2A skills, negotiate ACF placement with peer SDV, RSU, MNO, and Center agents, and dynamically adapt to changing road, network, and mission contexts. Conversely, the surrounding C-ITS and MNO infrastructure must evolve from static, message-based V2X delivery toward an intent-driven, agent-mediated control plane that can match the update cadence and behavioral diversity of fleets of SDVs. The Agentic AI framework defined here treats SDVs as first- class agentic participants rather than passive V2X clients. In C-ITS, distributed agents across vehicles, Road-Side Units (RSUs), and traffic management backends increasingly need to collaborate directly in an _Agent-to-Agent (A2A)_ manner for capability advertisement, peer discovery, task delegation, and state exchange. Emerging IETF work on Artificial Intelligence (AI) agent protocols formalizes such A2A interactions (e.g., messaging, capability schemas, and discovery) [I-D.rosenberg-ai-protocols], while the IRTF NMRG explores applicability of A2A to multi-domain network management and automation [I-D.jeong-nmrg-agentic-ai-framework][I-D.yang-nmrg-a2a-nm]. This approach provides a standards-based application/control-plane overlay for ACFs: vehicle, infrastructure, and cloud agents can discover and configure ACFs on programmable network devices, coordinate V2V/V2I compute placement, and exchange low-latency signals for admission control, safety services, and analytics, thereby reducing end-to-end delay and network overhead while improving interoperability and manageability in C-ITS deployments. The A2A paradigm itself has been actively discussed across recent IRTF NMRG meetings (e.g., IETF 124 and IETF 125), where a body of work on agentic AI, Large Language Model (LLM)-assisted operations, and agent-mediated control planes for networks has emerged. Representative directions include problem statements and motivations for agentic AI in network management [I-D.hong-nmrg-agenticai-ps], agentic AI architectural principles for autonomous networks [I-D.jadoon-nmrg-agentic-ai-autonomous-networks], agentic network architectures supporting agent interconnection and multi-level inference [I-D.chuyi-nmrg-agentic-network-inference], agent-driven Network Digital Twin (NDT) architectures [I-D.wmz-nmrg-agent-ndt-arch], agentic sensing and network optimization [I-D.bernardos-nmrg-agentic-network-optimization], and the applicability of model and tool-access protocols such as the Model Context Protocol (MCP) to network management An, et al. Expires 6 May 2027 [Page 4] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 [I-D.yang-nmrg-mcp-nm]. In parallel, industry initiatives (e.g., Google's A2A protocol) have contributed reference patterns for agent identity, capability cards (Agent Cards), task lifecycles, and secure peer-to-peer messaging that can be adopted as the application-layer substrate of an A2A overlay for C-ITS. Building on these trends, this document positions A2A as the primary coordination layer of the Agentic AI framework for SDV-centric C-ITS. Specifically, each major entity in the architecture (e.g., Center Cloud agents, C-ITS Infra agent, MNO agent, RSU agent, SDV agents, and VRU agent) hosts an AI agent that exposes standardized capability descriptions and exchanges intent-based requests over A2A. SDV agents in particular act as the bridge between in-vehicle software stacks (e.g., zonal controllers, AI/ADAS workloads, and IVN buses) and the external A2A overlay, so that vehicle-side software updates and capability changes are immediately reflected in the agent's advertised Agent Card. The Agentic AI interfaces (from I1 to I10) defined in this document are realized as A2A interactions between these agents, while the underlying transport, security, and policy enforcement continue to rely on existing C-ITS, V2X, and mobile network mechanisms. Therefore, this split keeps the agentic control plane aligned with the NMRG agentic-AI direction while preserving compatibility with deployed C-ITS, SDV, and MNO infrastructures. 2. Agentic AI Framework and Interfaces for SDV in C-ITS This section presents the detailed design of the Agentic AI framework and interfaces for Software-Defined Vehicles (SDVs) in C-ITS and MNO networking. 2.1. Agentic AI Framework for SDV, C-ITS, and MNO Networking Figure 1 shows the Agentic AI framework for SDV, C-ITS, and MNO networking. In this framework, every major functional entity hosts an AI _Agent_ that participates in an A2A overlay. SDV agents are first-class peers of infrastructure and operator agents: they advertise their in-vehicle software capabilities, sensing and compute resources, supported autonomy levels, and ACF requirements through signed Agent Cards. The A2A overlay provides capability advertisement (e.g., Agent Cards), peer discovery, intent/task delegation, and state exchange among agents, and is used to register, configure, monitor, and coordinate ACFs across the architecture. The A2A protocol runs as an application/control-plane overlay on top of the existing I1 to I10 interfaces; wired interfaces are typically depicted with solid links and wireless or A2A signalling with dashed links. An, et al. Expires 6 May 2027 [Page 5] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 * Central Cloud: A system that comprehensively controls the entire C-ITS (Cooperative Intelligent Transport Systems) environment. It manages information from various C-ITS centers, including regional centers and highway centers, and facilitates and oversees the connection between C-ITS data from the Government Public Center and end users. Additionally, it provides security functions through an integrated cybersecurity system. Within the Central Cloud, two cooperating agents (a C-ITS Center Agent and a Government Public Center Agent) participate in the A2A overlay to negotiate cross- domain data sharing and to delegate ACF configuration requests downward to the C-ITS Infra and MNO agents. * C-ITS Center: The C-ITS Center is a comprehensive term that encompasses both the Region Center and the Highway Center. It serves as the central hub for managing and coordinating intelligent transportation systems across various environments, including urban regions and highways. By integrating data from Region Centers and Highway Centers, the C-ITS Center ensures efficient traffic management, real-time data processing, and seamless communication between infrastructure and connected or autonomous vehicles. * Region Center: The Region Center refers to local centers established at key locations. These regional centers are connected to Roadside Units (RSUs) and function as one of the C-ITS Centers. Each regional C-ITS center collaborates with the Government Public Center to share collected data, ensuring seamless integration and data exchange between local infrastructure and centralized management systems. * Highway Center: The Highway Center operates similarly to the Region Center but is managed separately due to the unique characteristics of highways, which span multiple regions rather than being confined to a single city. Given the higher traffic volume on highways compared to regular roads, there is a significant increase in data generation, necessitating dedicated network management for highway environments. Highways are equipped with a greater number of RSUs than general roads, enabling the delivery of critical information to autonomous vehicles. As a result, the Highway Center focuses on managing areas that require more real-time processing to support safe and efficient autonomous driving. * Government Public Center: The Government Public Center is a C-ITS information provision system managed by the government. Due to the nature of road traffic infrastructure, it is challenging for private companies to manage this data effectively, and concerns over reliability make it difficult for users to utilize privately managed data. The Government Public Center ensures the delivery of highly reliable, government-provided data to users, enabling them to An, et al. Expires 6 May 2027 [Page 6] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 effectively utilize infrastructure-based information. It oversees the provision and management of trustworthy data essential for safe and efficient transportation systems. * C-ITS Data Linkage System: The C-ITS Data Linkage System is a platform designed to provide C-ITS data to external users. By offering data through methods such as Open APIs, this system connects C-ITS infrastructure information with users, enabling seamless access to real-time traffic and transportation data. It facilitates the integration of C-ITS data into various applications and services, supporting the development of innovative mobility solutions and enhancing the overall efficiency and safety of transportation systems. * Cyber Security System: The Cyber Security System is responsible for managing the security of communications between Software-Defined Vehicles (SDV), Vulnerable Road Users (VRU), RSU, Mobile Network Operators (MNO), and C-ITS infrastructure. Security technologies are fundamentally integrated into all communications to ensure encrypted data transmission. Outgoing data is encrypted using a public key, while receiving devices decrypt the data using a private key to securely access the information. The Cyber Security System oversees the protection of both private and public keys across all modules, ensuring robust security against potential exposure and safeguarding the integrity and confidentiality of transmitted data. In the A2A overlay, the Cyber Security System provides agent identity issuance, capability attestation, mutual authentication between agents, and revocation/rotation of agent credentials, so that all A2A interactions across I1 to I10 are cryptographically protected. * C-ITS Infra: The C-ITS Infrastructure is a system designed to collect and provide various types of information, including traffic signal data, roadside environment information, VRU data, and RSU data. The specific C-ITS information available may vary depending on the devices and equipments installed on the road. This infrastructure enables real-time data exchange between the transportation system and connected or autonomous vehicles, supporting safer and more efficient traffic management. A C-ITS Infra Agent fronts this subsystem in the A2A overlay, brokering interactions between Center Cloud agents (downstream policy and ACF configuration) and RSU/SDV/MNO agents (upstream telemetry and capability advertisement). * RSU: The RSU is a device that connects the C-ITS Infrastructure with SDVs. Through the RSU, SDVs can transmit and receive data between vehicles via V2V and between vehicles and infrastructure via V2I. RSUs play a critical role in enabling real-time communication, providing essential information such as traffic signals, road An, et al. Expires 6 May 2027 [Page 7] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 conditions, and safety alerts, thereby enhancing the safety and efficiency of autonomous and connected vehicle operations. Each RSU hosts a lightweight RSU Agent that participates in the A2A overlay to publish locally available ACFs (e.g., AI-based perception offload) and supporting tools (e.g., aggregation and filtering), discover SDV/ VRU agents within its coverage, and accept intent-based tasks delegated by the C-ITS Infra Agent or by neighboring SDV agents. * SDV1 and SDV2: SDV1 and SDV2 are examples depicted in the diagram, but in real-world scenarios, there can be an arbitrary number of vehicles. A Software-Defined Vehicle (SDV) is a vehicle whose functions (perception, planning, control, infotainment, diagnostics, and connectivity) are realized as software components running on a consolidated, zonal compute platform and are continuously updatable over the air. An SDV exposes two main communication interfaces: an External Communication Interface that enables communication with external systems such as RSUs, other vehicles (V2V), and infrastructure (V2I/V2N) for seamless interaction within the C-ITS ecosystem; and an Internal Vehicle Network (IVN) Interface that manages internal communication within the vehicle, connecting various onboard systems and components to ensure smooth operation and integration of vehicle functionalities. This dual-interface structure allows SDVs to efficiently exchange data both externally with the C-ITS infrastructure and internally for optimized vehicle control. Because vehicle-side software, models, and skills evolve continuously, an SDV's externally visible capabilities are intentionally agentic: the SDV hosts an in-vehicle SDV Agent that acts as the vehicle's representative in the A2A overlay, publishes a signed Agent Card that reflects the currently installed software/ skills, autonomy level, and safety class, negotiates ACF placement with RSU, MNO, and Center agents, and coordinates directly with other SDV agents for cooperative perception, platooning, and safety tasks. The SDV Agent also mediates between the IVN (zonal controllers, sensors, actuators) and the external A2A overlay, ensuring that only authorized, policy-bound intents reach in-vehicle subsystems. An, et al. Expires 6 May 2027 [Page 8] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 * IVN-Network1 and IVN-Network2: IVN-Network1 and IVN-Network2 are examples, but in practice, the internal communication system of a vehicle can consist of N different networks. These networks are part of the In-Vehicle Network (IVN), which facilitates communication within the vehicle. In an SDV (Software-Defined Vehicles), the IVN is designed based on a Zonal Architecture, where communication interfaces connect various devices and components within specific zones of the vehicle. This architecture improves data transmission efficiency, reduces wiring complexity, and enhances the integration of advanced systems for autonomous driving and vehicle control. Through this zonal design, SDVs can effectively manage high-speed data exchange between sensors, controllers, and actuators, supporting real-time processing and safer driving operations. * VRU: A VRU refers to users who can communicate either with an MNO or directly with SDVs. VRUs typically include pedestrians, cyclists, and motorcyclists who are more susceptible to traffic accidents due to their limited protection. By connecting with MNO networks, VRUs can receive real-time safety alerts and traffic information. Additionally, direct communication with SDVs enables VRUs to exchange critical safety data, such as location and movement intentions, which helps autonomous and connected vehicles detect and respond to nearby vulnerable users, ultimately enhancing road safety. A VRU Agent, typically hosted on the VRU's personal device, participates in the A2A overlay with a constrained capability profile, announcing presence and intent (e.g., crossing, joining traffic) to nearby SDV and MNO agents under privacy-preserving identifiers. * MNO: An MNO is a service provider that owns and manages wireless communication infrastructure, including network towers, core networks, and data centers. In the context of C-ITS, MNOs play a critical role in enabling real-time communication between vehicles, infrastructure, and VRUs by providing seamless connectivity through cellular networks (e.g., LTE, and 5G). MNOs facilitate the transmission of safety messages, traffic updates, and vehicle data, ensuring low-latency, high-reliability communication essential for autonomous driving and connected vehicle ecosystems. Additionally, MNOs collaborate with C-ITS infrastructure to enhance data security and manage network resources for efficient traffic management and mobility services. The MNO hosts an MNO Agent that exposes network- side capabilities (e.g., slice selection, QoS modulation, edge compute placement) over A2A, so that SDV, VRU, and Center agents can request connectivity and ACF execution in an intent-based, cross- domain manner. An, et al. Expires 6 May 2027 [Page 9] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 Center Cloud ******************************************************************** * * * +------------------+-----+ +-----+---------------------+ * * | C-ITS Center | | | | Government Public | * * |------------------| | I1 | | Center | * * | Region Center |Agent+<....>+Agent|---------------------| * * |------------------| | | | C-ITS Data Linkage | * * | Highway Center | | | |---------------------| * * | | | | | Cyber Security Sys | * * +------------------+--+--+ +--+--+---------------------+ * * ^ ^ * **************************:************:**************************** : I2 : I3 v v +------------+----+ +-+------------------------+ | Agent | | Agent | |-----------------|I4 |--------------------------| I7 +...>| C-ITS Infra |<...>| MNO | : +--------+--------+ +----------------+---------+ : ^ ^ ^ : : I5 I6 : I6 : : : : : v v v v +-----+-----+ I8 +-+--------------++ I9 +-----+---+-+ | RSU |Agent|<...>| Agent |<...>|Agent| VRU | +-----+-----+ |-----------------| +-----+-----+ | SDV1 | | IVN-Network1 | +-------+---------+ ^ : I10 : v +-----+-------+ | Agent | |-------------| | SDV2 | | IVN-Network2| +-------------+ <...> A2A Protocol Figure 1: Agentic AI Framework and Interfaces An, et al. Expires 6 May 2027 [Page 10] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 2.2. Agentic AI Interfaces According to the framework described in the previous section, there are major interfaces for Agentic AI coordination in C-ITS and MNO networking. Each interface listed below is realized as an A2A interaction between the two corresponding agents: the two agents authenticate each other using credentials issued by the Cyber Security System, exchange Agent Cards to learn each other's ACF- related capabilities, and then use intent-based request/response or publish/subscribe messages to register, configure, monitor, or invoke ACFs. The interface descriptions below therefore cover both the underlying data exchange and the A2A semantics layered on top. Interface 1 (I1): This is the registration interface between the C-ITS Center and the Government Public Center. It facilitates the exchange of C-ITS infrastructure data, such as traffic information and real-time road conditions, ensuring the Government Public Center can provide accurate and trustworthy data to external users. This interface also supports secure data sharing through standardized protocols and encryption. Interface 2 (I2): This interface connects the C-ITS Center with the C-ITS Infra. It is responsible for distributing infrastructure data, such as traffic signal information, road environment data, and RSU status, from the C-ITS Center to the C-ITS Infra for real-time processing and delivery to connected vehicles. It ensures continuous data flow for effective traffic and infrastructure management. Interface 3 (I3): This is the data exchange interface between the Government Public Center and the MNO (Mobile Network Operator). It enables the secure transmission of C-ITS data to MNOs, allowing mobile networks to deliver critical traffic and safety information to VRUs and vehicles. This interface must ensure data integrity and security during transmission. Interface 4 (I4): This interface connects the C-ITS Infra with the MNO. It supports the sharing of network resources and real-time communication between infrastructure components and mobile networks. This connection allows for efficient distribution of data, such as traffic alerts and safety notifications, to mobile users and vehicles. Interface 5 (I5): This is the communication interface between the C-ITS Infra and SDVs. It enables bidirectional data exchange, allowing SDVs to receive real-time infrastructure information (e.g., traffic signals, road hazards) and transmit vehicle status data back to the infrastructure. This interface is critical for supporting V2I communications. An, et al. Expires 6 May 2027 [Page 11] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 Interface 6 (I6): This interface connects the MNO with both VRUs and SDVs. It is used to deliver real-time safety messages, navigation updates, and other critical data. It also allows VRUs and SDVs to send status or emergency signals back to the network. This interface must ensure low-latency and secure data transmission to prevent accidents and improve traffic efficiency Interface 7 (I7): This is the management interface between the RSU and the C-ITS Infra. It facilitates the configuration, monitoring, and management of RSUs to ensure stable communication between roadside infrastructure and vehicles. It also handles firmware updates and diagnostics for RSUs. Interface 8 (I8): This interface supports V2I communication between SDVs through the RSU. It allows SDVs to exchange critical information such as speed, direction, and emergency signals, enabling collision avoidance and cooperative driving. This interface must provide real-time and reliable data exchange in dynamic traffic environments. Interface 9 (I9): This is the communication interface between SDVs and VRUs. It ensures that vulnerable road users receive immediate safety notifications from nearby vehicles and infrastructure. For example, SDVs can warn pedestrians of approaching vehicles or detect VRU movements in blind spots, enhancing road safety. Interface 10 (I10): This is the external and internal communication interface between multiple SDVs It enables secure and efficient communication within the vehicle's zonal architecture, facilitating seamless data exchange between various internal systems (e.g., sensors, controllers) and supporting autonomous driving functions. 3. Use Cases for Agentic AI in SDV and C-ITS This section introduces practical use cases of the Agentic AI framework in the context of Software-Defined Vehicles (SDVs), C-ITS, and MNO networking. These use cases focus on how the software- defined and continuously updatable nature of SDVs, combined with the A2A overlay, enables End-to-End (E2E) communication, cybersecurity, and cooperative driving services that adapt to vehicle, road, and network context in real time. * Real-Time Data Processing for SDV: The Agentic AI framework enables seamless communication between SDVs and C-ITS infrastructure through interfaces such as I5 (C-ITS Infra <-> SDV) and I8 (V2V Communication via RSU). Real-time data such as traffic signals, road conditions, and obstacle detection are transmitted to SDVs for immediate processing. By offloading certain data processing tasks to network An, et al. Expires 6 May 2027 [Page 12] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 devices (e.g., RSUs), SDVs can reduce internal computational load, allowing faster decision-making for functions like emergency braking or lane changes. This distributed data processing model improves the overall safety and efficiency of autonomous driving. * E2E Communication for Cooperative Driving: The integration of MNO networks with C-ITS through interfaces like I4 (C-ITS Infra <-> MNO) and I6 (MNO <-> VRU/SDV) allows for reliable and low-latency E2E communication. This connectivity is essential for cooperative driving scenarios, where multiple SDVs coordinate lane changes, merging, or platooning in real time. The Agentic AI framework ensures that the network can dynamically manage traffic loads and prioritize safety-critical data transmission, enabling vehicles to share and act on real-time information seamlessly. * Enhanced Cybersecurity for C-ITS and MNO Integration: Given the extensive data exchange between vehicles, infrastructure, and network operators, cybersecurity is a critical component. The Cyber Security System within the Agentic AI framework, managed through interfaces like I3 (Government Public Center <-> MNO) and I10 (Internal SDV Communication), provides E2E encryption and secure key management. Private keys are stored securely in the cloud and can be updated via Over-The-Air (OTA) mechanisms if compromised. If a critical security breach occurs, the system can initiate a global reset to reissue encryption keys, ensuring system-wide security integrity. This proactive approach minimizes the risk of cyberattacks on connected vehicles and infrastructure. * Dynamic Resource Allocation for High-Density Traffic Environments: In high-traffic conditions such as highways or urban intersections, efficient data management is crucial. The Agentic AI framework, through I7 (RSU <-> C-ITS Infra) and I9 (SDV <-> VRU), enables dynamic resource allocation. For example, RSUs can prioritize data transmission for emergency vehicles or redirect network resources to manage traffic congestion. This adaptive data flow management reduces latency and prevents network bottlenecks, ensuring that all vehicles and infrastructure components receive critical information in real time. An, et al. Expires 6 May 2027 [Page 13] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 * Edge Computing for Latency-Sensitive Applications: Edge computing capabilities are integrated into the Agentic AI framework using RSUs and Programmable Network Devices (PNDs) to handle latency-sensitive tasks. Interfaces like I1 (C-ITS Center <-> Government Public Center) and I8 (SDV <-> SDV via RSU) allow certain computational tasks such as object detection or predictive path planning to be processed at the network edge rather than relying on centralized cloud servers. This significantly reduces response time for autonomous driving actions and enhances road safety by enabling faster vehicle reactions. * These use cases demonstrate how the Agentic AI framework can enhance the performance, security, and reliability of intelligent transportation systems by integrating C-ITS infrastructure with MNO networks. By supporting real-time data processing, secure communication, and dynamic resource management, the framework addresses the complex demands of modern SDVs and connected mobility solutions. 4. A2A Use Cases for SDV-Centric C-ITS Integration In emerging SDV ecosystems, seamless coordination among vehicle agents, C-ITS infrastructure agents, and MNO agents becomes essential for achieving real-time awareness and adaptive network optimization. The _A2A_ communication paradigm enables direct interaction among these heterogeneous entities without relying solely on centralized control mechanisms. For instance, SDV agents can dynamically negotiate data offloading, perform network slicing, or compute resource scheduling with MNO agents in response to vehicular mobility and network conditions, while roadside infrastructure agents exchange situational context such as congestion level, edge compute availability, or safety alerts with SDV agents to support cooperative perception and hazard prediction. These A2A interactions facilitate distributed decision-making across application and network layers, forming the basis for intelligent coordination and resilient service continuity in connected mobility. When integrated with the proposed Agentic AI framework, such A2A- based orchestration allows SDVs, RSUs, and MNO backends to jointly manage ACFs, thereby ensuring low-latency, secure, and reliable service delivery across multi-domain C-ITS environments. This approach follows recognized architectures and standards used in C-ITS and V2X systems, including frameworks for security management and network data analytics. Leveraging these industry standards, A2A coordination can extend beyond individual domains to enable intent- driven, cross-layer management of communication, computation, and data analytics among SDV, C-ITS, and MNO ecosystems. An, et al. Expires 6 May 2027 [Page 14] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 The following use cases illustrate concrete A2A interaction patterns on top of the Agentic AI framework. They are intentionally aligned with the agentic-AI direction discussed in the IRTF NMRG at IETF 124 and IETF 125, and with the broader industry A2A reference patterns (e.g., Agent Cards, task lifecycles, and secure peer-to-peer messaging) so that C-ITS deployments can interoperate with general- purpose AI agent ecosystems. * Capability Advertisement and Discovery (I2, I4, I5, I7): C-ITS Infra Agent, MNO Agent, RSU Agents, and SDV Agents publish Agent Cards describing the ACFs they host (e.g., AI-based perception offload) and their supporting skills (e.g., message aggregation, slice selection, and OTA key rotation). Center Cloud agents index these cards via I2/I3 and use them to plan ACF placement. Discovery is intent-driven: an SDV Agent requesting "low-latency cooperative perception within 100 ms" is matched with nearby RSU/MNO agents whose Agent Cards advertise compatible ACFs. * Cooperative Perception via SDV-to-SDV and SDV-to-RSU A2A (I8, I10): SDV agents directly negotiate sensor data exchange, fusion responsibility, and confidence reporting with neighboring SDV agents (I10) and RSU agents (I8). Heavy fusion ACFs can be delegated to the RSU Agent when the SDV is compute-constrained, while the SDV Agent retains decision authority. This pattern mirrors the agent- interconnection and multi-level inference approach discussed in [I-D.chuyi-nmrg-agentic-network-inference]. For cooperative perception, an SDV Agent selects an advertised RSU or MEC processing function and sends the region of interest, processing deadline, and required output format. The provider checks the request conditions and available resources, and returns acceptance with a task identifier or rejection with a reason. After acceptance, the provider invokes the ACF and reports its processing status. A completed result includes the observation time, source, and quality information so that the SDV can combine it with its own observations. Agent coordination uses an IP-capable path, including connectivity through LTE or 5G mobile networks. LTE-V2X and NR-V2X PC5 can carry vehicle and roadside data in the same deployment. The coordination path and the observation or result data path can differ, depending on the available connectivity and application mapping. An, et al. Expires 6 May 2027 [Page 15] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 * Intent-Based Slice and Edge Negotiation with MNO (I4, I6): An SDV Agent or a VRU Agent expresses a high-level intent (e.g., "platooning session, 50 vehicles, end-to-end latency budget 20 ms, reliability 99.999 percent") to the MNO Agent via A2A. The MNO Agent translates the intent into slice configuration and edge ACF placement, consistent with the agentic network optimization patterns described in [I-D.bernardos-nmrg-agentic-network-optimization]. * Cross-Domain Safety Coordination (I3, I6, I9): When a Government Public Center Agent detects a hazardous event, it issues an A2A task to the MNO Agent and C-ITS Infra Agent, which fan out the task to local RSU and SDV agents. VRU agents in the affected area receive targeted alerts via I6/I9 under privacy-preserving identifiers provided by the Cyber Security System. * Agentic Network Digital Twin for C-ITS (I1, I2, I4): Center Cloud agents maintain an agentic NDT of the C-ITS network and use it to simulate ACF placement before pushing configurations to C-ITS Infra and MNO agents. This use case aligns with the agent-driven NDT architecture in [I-D.wmz-nmrg-agent-ndt-arch] and with the problem statement for agentic AI in network management in [I-D.hong-nmrg-agenticai-ps]. * Tool-Augmented Agent Operations via MCP (all interfaces): Agents may expose their local management tools (e.g., RSU firmware update, SDV diagnostic, slice reconfiguration) as MCP-style tools, and other agents may invoke them under A2A authorization. The applicability of MCP to such network management tasks is discussed in [I-D.yang-nmrg-mcp-nm]; the Agentic AI framework reuses this pattern to keep tool invocation auditable and policy-bound. * Autonomous Reaction and Human-in-the-Loop Oversight: Following the agentic-AI architectural principles in [I-D.jadoon-nmrg-agentic-ai-autonomous-networks], Agentic AI agents operate within explicit autonomy levels. Routine reconfiguration of ACFs or supporting services (e.g., adjusting aggregation thresholds at an RSU) runs autonomously, while safety-critical reconfiguration (e.g., revoking a compromised agent or resetting cryptographic material) requires escalation to a Center Cloud agent and, where appropriate, a human operator. An, et al. Expires 6 May 2027 [Page 16] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 5. Agent Cards for SDVs and C-ITS Entities Following the A2A protocol model adopted by [I-D.yang-nmrg-a2a-nm], every agent in the Agentic AI framework MUST publish an Agent Card: a JSON metadata document that describes the agent's identity, endpoint, advertised ACF-related capabilities, skills, and authentication requirements. Agent Cards are the basis for capability discovery and intent matching across I1 to I10. Agent Cards are signed and attested by the Cyber Security System and SHOULD be discoverable by peer agents either via a well-known URI on the hosting entity or via a Center Cloud registry. The following non-normative examples illustrate Agent Cards for representative C-ITS entities. The illustrative "capabilities" field lists ACF and supporting-service classes exposed by the agent, and "skills" enumerate concrete actions invocable through A2A messages. { "name": "RSUAgent-01", "description": "RSU agent for AI perception offload and message aggregation.", "url": "https://rsu-01.cits.example.net/a2a/tasks", "capabilities": ["PerceptionOffload", "MessageAggregation", "V2X-Relay"], "skills": [ { "id": "offload_perception", "name": "Cooperative perception offload", "description": "Run sensor fusion on behalf of an SDV within RSU coverage.", "inputModes": ["application/json", "text/structured"], "outputModes": ["application/json", "text/status"] }, { "id": "aggregate_cam", "name": "CAM/BSM aggregation", "description": "Aggregate and forward V2X awareness messages to the C-ITS Infra.", "inputModes": ["application/json"], "outputModes": ["text/status"] } ] } Figure 2: Example Agent Card: RSU Agent An, et al. Expires 6 May 2027 [Page 17] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 { "name": "SDVAgent-VIN-XYZ", "description": "In-vehicle SDV agent for cooperative driving over A2A.", "url": "https://sdv-xyz.veh.example.net/a2a/tasks", "capabilities": ["CooperativePerception", "Platooning", "Telemetry", "OTA-KeyRotation"], "skills": [ { "id": "request_perception", "name": "Request cooperative perception", "description": "Request fused object lists from nearby RSU or SDV agents.", "inputModes": ["application/json"], "outputModes": ["application/json"] }, { "id": "join_platoon", "name": "Join platoon", "description": "Negotiate joining a platoon with neighboring SDV agents.", "inputModes": ["application/json"], "outputModes": ["text/status"] } ] } Figure 3: Example Agent Card: SDV Agent An, et al. Expires 6 May 2027 [Page 18] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 { "name": "MNOAgent-OpA", "description": "MNO agent for C-ITS slice selection and edge ACF placement.", "url": "https://mno-a.example.net/a2a/tasks", "capabilities": ["NetworkSlicing", "EdgeACFPlacement", "QoSModulation"], "skills": [ { "id": "select_slice", "name": "Slice selection", "description": "Select or instantiate a network slice matching the requested intent.", "inputModes": ["application/json"], "outputModes": ["application/json"] }, { "id": "place_edge_acf", "name": "Edge ACF placement", "description": "Place an ACF on an MEC node close to the requesting SDV/VRU agent.", "inputModes": ["application/json"], "outputModes": ["text/status"] } ] } Figure 4: Example Agent Card: MNO Agent For a cooperative-perception capability, the Agent Card's skill identifier and name identify the offered function, while its input and output modes describe the supported formats. The associated ACF descriptor additionally identifies the processing region and endpoint. The "acf-descriptor" container below represents this information. A request refers to the advertised capability using "capability-id". The descriptor can be carried in or referenced from the Agent Card according to the selected A2A version. 6. YANG-based Structured Data for A2A Communication in SDV and C-ITS While the A2A protocol natively supports unstructured textual content for inter-agent exchange, the orchestration of ACFs and supporting services in C-ITS demands clarity, unambiguous intent transmission, and machine-interpretable data, especially when safety-critical actuation (e.g., emergency rerouting, key revocation, slice reconfiguration) is involved. Natural-language-only payloads carry the inherent ambiguity of human language and can lead to inconsistent ACF configuration or large-scale service degradation, which is unacceptable for C-ITS. An, et al. Expires 6 May 2027 [Page 19] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 This document adopts the approach of [I-D.yang-nmrg-a2a-nm], which uses YANG [RFC7950] as the structured data layer for A2A payloads, with NETCONF [RFC6241] and RESTCONF [RFC8040] as candidate underlying management protocols when an agent needs to actuate an ACF on a programmable network device. Building on that approach, this document defines a non-normative YANG module, "ietf-cits-acf-intent", whose data nodes are carried inside the "data" part of A2A messages exchanged across I1 to I10. The module provides a machine- interpretable representation of C-ITS ACF intents and supplements the natural-language "text" parts that the same A2A message may carry. The intent is that an SDV, RSU, MNO, or Center agent that receives an A2A message can validate the "data" part against this YANG module before acting upon it, and can use existing NETCONF or RESTCONF tooling to persist or actuate the intent on a programmable network device. In the C-ITS context, YANG-modeled payloads carried as the "data" part of A2A messages are RECOMMENDED for the following content categories: * ACF descriptors (capability schemas of RSU/MNO/SDV ACFs), and their supporting services, modeled by the "acf-descriptor" container of "ietf-cits-acf-intent". * C-ITS intent objects (e.g., platooning, cooperative perception, hazard alert) expressed as structured intents under the "cits-acf- intents" container of "ietf-cits-acf-intent". * Telemetry and incident reports between RSU/SDV agents and Center Cloud agents, reusing the YANG model in [I-D.ietf-nmop-network-incident-yang] where applicable. * Cryptographic material lifecycle events (rotation, revocation) managed by the Cyber Security System. The cooperative-perception exchange uses the existing intent object for Request, Response, and Result information. The Request uses "intent-id" as its request identifier and adds "capability-id" and "output-format" to the existing region and deadline fields. The Response carries the same "intent-id", an accepted or rejected status, and a "task-id" when accepted. A rejected request includes a "reason" and does not allocate a task identifier. After execution, the Result retains the request and task identifiers and reports completed or failed status. The added "result" container carries a result reference, output format, observation time, source identifiers, and a quality metric and value. The metric identifies how to interpret the quality value. The SDV checks these fields and An, et al. Expires 6 May 2027 [Page 20] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 the result's age before using the information. For cooperative perception, "response-deadline" denotes the latest acceptable receipt time of the processing result; admission is reported before that time. The added fields are optional in the module skeleton so that existing intent objects remain representable. A cooperative- perception request supplies the selected capability and output format. Its provider assigns a task identifier after acceptance and supplies the result information on completion. These data fields supplement the existing A2A message and task mechanisms. The module name, namespace, prefix, and local identifiers below use ACF terminology. These illustrative names are a proposal, not registered or finalized identifiers. The model includes supporting service classes such as NetworkSlicing and OTAKeyRotation; those classes do not imply that the underlying operation uses AI. Renaming the earlier module is a schema and namespace change, not a backward- compatible alias. Implementations using earlier names would require an explicit migration mapping. The high-level tree structure of the "ietf-cits-acf-intent" module, expressed using the YANG tree diagram notation, is shown in Figure 5. The corresponding YANG module skeleton is shown in Figure 6. Both artifacts are non-normative and are intended as a starting point for a companion YANG document. module: ietf-cits-acf-intent +--ro acf-descriptor | +--ro capability* [capability-id] | +--ro capability-id string | +--ro function-name? string | +--ro endpoint? string | +--ro input-format* string | +--ro output-format* string | +--ro service-region* string | +--ro region-reference? string +--rw cits-acf-intents +--rw intent* [intent-id] +--rw intent-id string +--rw type identityref +--rw requester string +--rw target-acf identityref +--rw capability-id? string +--rw output-format? string +--rw safety-class? enumeration +--rw priority? uint8 An, et al. Expires 6 May 2027 [Page 21] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 +--rw response-deadline? yang:date-and-time +--rw interface? enumeration +--rw constraints | +--rw max-latency-ms? uint32 | +--rw min-reliability? decimal64 | +--rw min-confidence? decimal64 | +--rw region-of-interest? string | +--rw bandwidth-mbps? uint32 | +--rw max-data-age-ms? uint32 | +--rw region-reference? string | +--rw quality-metric? string +--rw participants* string +--ro task-id? string +--ro reason? string +--ro result | +--ro result-reference? string | +--ro output-format? string | +--ro observation-time? yang:date-and-time | +--ro source-id* string | +--ro quality-metric? string | +--ro quality-value? decimal64 +--ro status? enumeration +--ro last-updated? yang:date-and-time notifications: +---n acf-intent-event +--ro intent-id -> /cits-acf-intents/intent/intent-id +--ro event-type enumeration +--ro task-id? string +--ro reason? string +--ro details? string Figure 5: YANG Tree Diagram of ietf-cits-acf-intent module ietf-cits-acf-intent { yang-version 1.1; namespace "urn:ietf:params:xml:ns:yang:ietf-cits-acf-intent"; prefix "cits-acf"; import ietf-yang-types { prefix yang; } organization "IETF NMRG (Network Management Research Group)"; contact "WG Web: Editor: Byoungman An An, et al. Expires 6 May 2027 [Page 22] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 Editor: Jaehoon Paul Jeong "; description "This YANG module defines a data model for representing Cooperative Intelligent Transportation System (C-ITS) AI Computing Function (ACF) intents that are carried as the 'data' part of Agent-to-Agent (A2A) messages between SDV, RSU, MNO, VRU, and Center agents of the Agentic AI framework."; revision 2026-11-02 { description "Align the illustrative module, namespace, and identifiers with ACF terminology in the Agentic AI framework; distinguish ACFs from supporting services."; reference "draft-an-nmrg-i2icf-cits-03"; } revision 2026-10-27 { description "Add capability, request, response, and result fields for SDV-to-RSU/MEC cooperative perception."; reference "draft-an-nmrg-i2icf-cits-03"; } revision 2026-02-05 { description "Initial revision."; reference "draft-an-nmrg-i2icf-cits-02"; } /* Identities for ACF intent types and target ACF classes */ identity intent-type { description "Base identity for C-ITS ACF intent types."; } identity cooperative-perception { base intent-type; description "Cooperative perception intent (e.g., SDV-RSU)."; } identity platooning { base intent-type; description "Platooning session intent among SDVs."; } identity hazard-alert { base intent-type; description "Hazard alert dissemination intent."; } identity slice-request { base intent-type; description "Network slice/edge ACF placement intent to MNO."; An, et al. Expires 6 May 2027 [Page 23] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 } identity ota-key-rotation { base intent-type; description "OTA key rotation intent managed by the Cyber Security System."; } identity acf-class { description "Base identity for ACF or supporting-service classes."; } identity PerceptionOffload { base acf-class; } identity MessageAggregation { base acf-class; } identity NetworkSlicing { base acf-class; } identity EdgeACFPlacement { base acf-class; } identity OTAKeyRotation { base acf-class; } /* Top-level data tree */ container acf-descriptor { config false; description "Advertised ACFs and supporting services of the hosting agent."; list capability { key "capability-id"; description "One computing function offered by the agent."; leaf capability-id { type string; description "Identifier of the advertised function or service."; } leaf function-name { type string; description "Name of the offered processing function."; } leaf endpoint { type string; description "Endpoint for requesting the function."; } leaf-list input-format { type string; description "Supported input representations."; } leaf-list output-format { type string; description "Supported output representations."; } leaf-list service-region { type string; description "Regions for which processing is offered."; An, et al. Expires 6 May 2027 [Page 24] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 } leaf region-reference { type string; description "Coordinate or map reference for the regions."; } } } container cits-acf-intents { description "Collection of C-ITS ACF intents currently known to the hosting agent."; list intent { key "intent-id"; description "A single C-ITS ACF intent."; leaf intent-id { type string; description "Globally unique intent identifier."; } leaf type { type identityref { base intent-type; } mandatory true; description "Intent type (e.g., cooperative-perception)."; } leaf requester { type string; mandatory true; description "Agent name of the requesting agent."; } leaf target-acf { type identityref { base acf-class; } mandatory true; description "Targeted ACF or supporting-service class."; } leaf capability-id { type string; description "Selected capability advertised by the provider."; } leaf output-format { type string; description "Requested result representation."; } leaf safety-class { type enumeration { enum QM; enum ASIL-A; enum ASIL-B; enum ASIL-C; enum ASIL-D; } An, et al. Expires 6 May 2027 [Page 25] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 description "ISO 26262 ASIL classification of the intent."; } leaf priority { type uint8 { range "0..7"; } description "Relative priority (0 = lowest)."; } leaf response-deadline { type yang:date-and-time; description "Latest acceptable response time."; } leaf interface { type enumeration { enum I1; enum I2; enum I3; enum I4; enum I5; enum I6; enum I7; enum I8; enum I9; enum I10; } description "Agentic AI interface over which the intent flows."; } container constraints { description "Operational constraints attached to the intent."; leaf max-latency-ms { type uint32; units "milliseconds"; } leaf min-reliability { type decimal64 { fraction-digits 5; } } leaf min-confidence { type decimal64 { fraction-digits 2; } } leaf region-of-interest { type string; } leaf bandwidth-mbps { type uint32; units "Mbit/s"; } leaf max-data-age-ms { type uint32; units "milliseconds"; description "Maximum observation age at result receipt."; } leaf region-reference { type string; description "Coordinate or map reference for the region."; } leaf quality-metric { type string; description "Definition used to interpret min-confidence."; } } leaf-list participants { type string; description "Other agents participating in this intent."; } leaf task-id { type string; config false; description "Provider-assigned identifier after acceptance."; } leaf reason { type string; An, et al. Expires 6 May 2027 [Page 26] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 config false; description "Reason for rejection, failure, or expiry."; } container result { config false; description "Information returned for a completed task."; leaf result-reference { type string; description "Reference to the processing result."; } leaf output-format { type string; description "Representation of the returned result."; } leaf observation-time { type yang:date-and-time; description "Earliest observation contributing to result."; } leaf-list source-id { type string; description "Sources contributing to the result."; } leaf quality-metric { type string; description "Definition used to interpret quality-value."; } leaf quality-value { type decimal64 { fraction-digits 5; } description "Quality under the identified metric."; } } leaf status { type enumeration { enum requested; enum accepted; enum running; enum completed; enum failed; enum revoked; enum rejected; enum expired; } config false; description "Lifecycle status of the intent."; } leaf last-updated { type yang:date-and-time; config false; description "Time of the last status update."; } } } An, et al. Expires 6 May 2027 [Page 27] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 /* Event-driven A2A notification */ notification acf-intent-event { description "Notification emitted when an intent changes state, used by event-driven A2A pub/sub channels (see Section 'Event-driven A2A for Safety Signalling')."; leaf intent-id { type leafref { path "/cits-acf:cits-acf-intents/cits-acf:intent" + "/cits-acf:intent-id"; } } leaf event-type { type enumeration { enum accepted; enum rejected; enum progress; enum completed; enum failed; enum revoked; enum expired; } } leaf task-id { type string; description "Task identifier assigned on acceptance."; } leaf reason { type string; description "Reason for an unsuccessful outcome."; } leaf details { type string; } } } Figure 6: YANG Module Skeleton: ietf-cits-acf-intent The following non-normative example illustrates an A2A message sent from an SDV Agent to an RSU Agent over I8 to request a cooperative perception ACF. The "data" part carries an instance of the "ietf- cits-acf-intent" YANG module shown above, encoded as JSON per [RFC7951], using the media type "application/yang-data+json" defined in [RFC8040], while the "text" part preserves a human-readable summary. POST /a2a/tasks HTTP/1.1 Host: rsu-01.cits.example.net Content-Type: application/json { "jsonrpc": "2.0", "method": "message/send", An, et al. Expires 6 May 2027 [Page 28] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 "params": { "message": { "message_id": "c1ts-7f3e-4a21-9b12-0e2d6a8c4f10", "context_id": "intersection-42:approach-east", "role": "ROLE_USER", "parts": [ { "text": "Cooperative perception within 100 ms: intersection-42 eastbound.", "media_type": "text/plain" }, { "data": { "ietf-cits-acf-intent:cits-acf-intents": { "intent": [ { "intent-id": "intent-9921", "type": "ietf-cits-acf-intent:cooperative-perception", "requester": "SDVAgent-VIN-XYZ", "target-acf": "ietf-cits-acf-intent:PerceptionOffload", "capability-id": "offload_perception", "output-format": "application/json", "safety-class": "ASIL-B", "priority": 6, "response-deadline": "2026-02-10T06:00:00Z", "interface": "I8", "constraints": { "max-latency-ms": 100, "min-confidence": "0.85", "quality-metric": "fusion-confidence-v1", "max-data-age-ms": 150, "region-reference": "intersection-map-v1", "region-of-interest": "intersection-42:east" }, "participants": ["RSUAgent-01"] } ] } }, "media_type": "application/yang-data+json", "metadata": { "yang_module": "ietf-cits-acf-intent", "revision": "2026-11-02" } } An, et al. Expires 6 May 2027 [Page 29] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 ] }, "configuration": { "accepted_output_modes": ["application/yang-data+json", "text/status"], "blocking": false, "history_length": 3 }, "metadata": { "request_type": "acf_invocation", "priority": "high", "response_deadline": "2026-02-10T06:00:00Z" } } } Figure 7: A2A Message Example with YANG-structured Data (I8: SDV to RSU) The YANG module shown above is non-normative and is expected to be refined in a companion YANG document, reusing IETF building blocks for incident management [I-D.ietf-nmop-network-incident-yang] and existing C-ITS/V2X data dictionaries. 7. Operational Considerations The introduction of an A2A overlay within the Agentic AI framework has several operational implications that need to be considered when deploying the architecture in large-scale, safety-critical C-ITS environments. This section is aligned with the operational considerations discussed in [I-D.yang-nmrg-a2a-nm] and adapts them to C-ITS. 7.1. Agent Skills as Expertise Expansion General-purpose AI agents do not natively possess C-ITS domain expertise (e.g., V2X message semantics, RSU operational procedures, MNO slice templates). C-ITS operators SHOULD package such expertise as Agent Skills (e.g., the "diagnose_rsu_link_loss" or "build_platoon_session" skill) so that a generic Agentic AI agent can be specialized for a given deployment without re-training the underlying model. Skills SHOULD be versioned and signed so that the Cyber Security System can attest the skill set advertised in an Agent Card. An, et al. Expires 6 May 2027 [Page 30] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 7.2. Knowledge Base as Ground Truth Data To mitigate hallucinations of LLM-based agents, deployments SHOULD provide a shared, machine-interpretable knowledge base covering C-ITS topology, RSU/SDV configuration baselines, MNO slice templates, regulatory policies, and historical incident records. Agents retrieve from this knowledge base when reasoning over A2A tasks. The Model Context Protocol (MCP) [I-D.yang-nmrg-mcp-nm] is a candidate substrate for standardized knowledge-base access in this framework. 7.3. Event-driven A2A for Safety Signalling The task-based A2A request/response model is sufficient for slow-loop ACF configuration but insufficient for safety-critical C-ITS events (e.g., emergency electronic brake, hazard detection). For such events, agents SHOULD also support an event-driven publish/subscribe pattern, where a Hazard Agent publishes to a topic on a message broker and interested SDV, RSU, MNO, and Center agents subscribe to receive near-real-time notifications. This pattern reuses the event- driven A2A architecture described in [I-D.yang-nmrg-a2a-nm]. 7.4. Scalability A national-scale C-ITS deployment may include thousands of RSUs, millions of SDVs and VRUs, and multiple cooperating MNOs. A2A messaging volume is therefore significantly higher than static RPC- based interfaces. Operators SHOULD: * Adopt hierarchical/federated agent structures so that local decisions (e.g., intersection-level cooperative perception) remain local to RSU and SDV agents. * Apply rate-limiting, backoff, and prioritization on A2A messages, with the highest priority reserved for safety signalling. * Localize Agent Card registries per region (e.g., per Region Center or Highway Center) to avoid global discovery hotspots. 7.5. Latency and Performance Constraints Many C-ITS use cases (cooperative perception, platooning, intersection management) impose tight end-to-end timing budgets (tens of milliseconds). Implementations SHOULD define performance envelopes for: * Maximum A2A message processing latency for each interface (I1 to I10). An, et al. Expires 6 May 2027 [Page 31] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 * Timeout and retry behavior, with deterministic fallback to direct controller APIs or pre-provisioned static ACF configurations when A2A interactions cannot meet the deadline. * Bounded LLM inference time when an agent relies on generative reasoning; safety-critical paths SHOULD NOT depend on unbounded LLM inference. 7.6. Reliability and Failure Handling A2A workflows in C-ITS may span vehicles entering and leaving coverage, intermittent wireless links, and partial cloud failures. Implementations SHOULD provide: * Workflow checkpointing so that long-lived tasks (e.g., a platoon session) can survive agent restarts. * Idempotent retry semantics for ACF invocations. * Transactional ACF reconfiguration with confirmed-commit-like semantics (analogous to NETCONF confirmed-commit) when multiple devices must be updated atomically. * Circuit breakers and automatic escalation to a human operator when sustained failures threaten safety. For cooperative-perception requests, the provider uses the authenticated requester and "intent-id" to recognize a retry of the same request. While the request record is retained, it returns the recorded decision or task status without starting a second execution. Reuse of that identifier with different request conditions is rejected with a reason. Retention covers at least the request's response deadline. If the deadline is reached before completion, the provider reports expired status and a reason. Failed or expired tasks retain the assigned task identifier. The SDV does not use a result received after its deadline or maximum data-age limit. For a completed task, the returned output format matches the accepted request, and its source and quality information remain associated with the same request and task identifiers. An, et al. Expires 6 May 2027 [Page 32] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 7.7. Agent Lifecycle and Resource Management Agentic AI agents are long-running production components and require lifecycle management: onboarding and registration through the Cyber Security System, controlled model/skill updates (with rollback), decommissioning, and revocation of compromised agents through the same OTA mechanism used for cryptographic key rotation. Operators SHOULD monitor agent resource consumption (CPU, memory, inference workload), especially on constrained RSU and SDV platforms. 7.8. Inter-Domain Operational Challenges C-ITS is inherently multi-domain: Government Public Center, Region/ Highway Centers, multiple MNOs, vehicle OEMs, and third-party service providers may each operate independent agent populations. Cross- domain A2A interactions therefore require: * Federated trust establishment among Cyber Security Systems of different domains. * Interoperable Agent Card schemas and YANG models for ACF intents. * Policy reconciliation (e.g., differing privacy regulations for VRU data) before sharing tasks across administrative boundaries. * Auditing and accountability records for every cross-domain A2A invocation, retained by the receiving domain. 8. IANA Considerations TBD. 9. Security Considerations The Agentic AI framework for C-ITS and MNO Networking offers numerous advantages for various applications. However, due to the framework's extensive connectivity between diverse vehicles, devices, centers, clouds, and VRUs, a vast amount of information and functionalities are exposed during network configuration, leading to potential security risks. To ensure the overall security of the entire system, the following measures are recommended: First, the application development system should be controlled by the same service providers (e.g., cloud service providers or network operators) that own the network and computing infrastructure. Second, devices within the cloud center should be pre-configured with security zones to isolate traffic, preventing it from affecting other network traffic. Third, encryption keys for each device should be centrally managed by the cloud center. In the event of key exposure, the system should An, et al. Expires 6 May 2027 [Page 33] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 support Over-The-Air (OTA) updates to promptly replace compromised keys. Fourth, if a security breach occurs within the centralized management system, exposing encryption keys, the entire system should undergo a reset to perform a security initialization. This process will generate and distribute new encryption keys to ensure the continued protection of sensitive data. Introducing an A2A overlay within the Agentic AI framework adds further security-sensitive surfaces that need to be addressed. Each agent MUST have a verifiable identity and a signed Agent Card whose contents (e.g., advertised ACFs, supported intents, authorization scopes) are authenticated by the Cyber Security System. A2A messages between agents MUST be mutually authenticated, integrity-protected, and confidentiality-protected, and SHOULD carry replay protection suitable for vehicular environments. Agents SHOULD operate under a least-privilege capability model: an SDV Agent cannot reconfigure RSU or MNO ACFs unless explicitly authorized, and a compromised agent's credentials MUST be revocable through the same OTA mechanism used for cryptographic key rotation. Finally, because A2A may carry LLM- generated or LLM-influenced content, deployments SHOULD apply input validation, prompt-injection mitigation, and human-in-the-loop oversight for safety-critical decisions, consistent with the agentic- AI principles discussed in [I-D.jeong-nmrg-agentic-ai-framework], [I-D.jadoon-nmrg-agentic-ai-autonomous-networks], and [I-D.hong-nmrg-agenticai-ps]. 10. References 10.1. Normative References [RFC2119] Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, RFC 2119, DOI 10.17487/RFC2119, March 1997, . [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, . [RFC7950] Bjorklund, M., Ed., "The YANG 1.1 Data Modeling Language", RFC 7950, DOI 10.17487/RFC7950, August 2016, . [RFC7951] Lhotka, L., "JSON Encoding of Data Modeled with YANG", RFC 7951, DOI 10.17487/RFC7951, August 2016, . An, et al. Expires 6 May 2027 [Page 34] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 [RFC8040] Bierman, A., Bjorklund, M., and K. Watsen, "RESTCONF Protocol", RFC 8040, DOI 10.17487/RFC8040, January 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, . [RFC8799] Carpenter, B. and B. Liu, "Limited Domains and Internet Protocols", RFC 8799, DOI 10.17487/RFC8799, July 2020, . 10.2. Informative References [I-D.bernardos-nmrg-agentic-network-optimization] Bernardos, C. J., Mourad, A., and M. A. Jadoon, "Solutions for enabling agentic sensing with network optimization", Work in Progress, Internet-Draft, draft-bernardos-nmrg- agentic-network-optimization-02, 2 October 2026, . [I-D.chuyi-nmrg-agentic-network-inference] Guo, C., "Agentic Network Architecture and Protocol for Supporting Agent Interconnection Communication and Multi- level Inference", Work in Progress, Internet-Draft, draft- chuyi-nmrg-agentic-network-inference-01, 6 July 2026, . [I-D.hong-nmrg-agenticai-ps] Hong, Y., Youn, J., Wu, Q., and B. Claise, "Motivations and Problem Statement of Agentic AI for network management", Work in Progress, Internet-Draft, draft-hong- nmrg-agenticai-ps-02, 5 July 2026, . [I-D.ietf-nmop-network-incident-yang] Hu, T., Contreras, L. M., Wu, Q., Davis, N., and C. Feng, "A YANG Data Model for Network Incident Management", Work in Progress, Internet-Draft, draft-ietf-nmop-network- incident-yang-20, 16 October 2026, . An, et al. Expires 6 May 2027 [Page 35] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 [I-D.irtf-coinrg-use-cases] Kunze, I., Wehrle, K., Trossen, D., Montpetit, M., de Foy, X., Griffin, D., and M. Rio, "Use Cases for In-Network Computing", Work in Progress, Internet-Draft, draft-irtf- coinrg-use-cases-07, 4 December 2024, . [I-D.jadoon-nmrg-agentic-ai-autonomous-networks] Jadoon, M. A., Robitzsch, S., and C. J. Bernardos, "Agentic AI Architectural Principles for Autonomous Computer Networks", Work in Progress, Internet-Draft, draft-jadoon-nmrg-agentic-ai-autonomous-networks-00, 2 March 2026, . [I-D.jeong-nmrg-agentic-ai-framework] Jeong, J. P., Gu, M., Ahn, Y., Park, J., and B. R. An, "An Agentic AI Framework for the Management of Networks, Security, and AI Services", Work in Progress, Internet- Draft, draft-jeong-nmrg-agentic-ai-framework-00, 2 November 2026, . [I-D.rosenberg-ai-protocols] 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, . [I-D.wmz-nmrg-agent-ndt-arch] Wu, Q., Zhou, C., Contreras, L. M., Han, S., and Y. Hong, "Network Digital Twin and Agentic AI based Architecture for AI-driven Network Operations", Work in Progress, Internet-Draft, draft-wmz-nmrg-agent-ndt-arch-06, 28 August 2026, . [I-D.yang-nmrg-a2a-nm] Lopez, D., Moreno, N. R., Tailhardat, L., Ma, Q., Wu, Q., Yang, Y., and S. Prabhu, "Applicability of A2A to the Network Management", Work in Progress, Internet-Draft, draft-yang-nmrg-a2a-nm-04, 2 November 2026, . An, et al. Expires 6 May 2027 [Page 36] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 [I-D.yang-nmrg-mcp-nm] Yang, Y., Wu, Q., Lopez, D., Moreno, N. R., Tailhardat, L., and S. Prabhu, "Applicability of MCP for the Network Management", Work in Progress, Internet-Draft, draft-yang- nmrg-mcp-nm-04, 2 November 2026, . [I-D.yao-tsvwg-cco-problem-statement-and-usecases] Yao, K., Shiping, X., Li, Y., Huang, H., and D. KUTSCHER, "Collective Communication Optimization: Problem Statement and Use cases", Work in Progress, Internet-Draft, draft- yao-tsvwg-cco-problem-statement-and-usecases-00, 23 October 2023, . Acknowledgments 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-2024-00397615, Development of an automotive software platform for Software-Defined- Vehicle (SDV) integrated with an AI framework required for intelligent vehicles). This work was in part supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea MSIT (No. RS-2024-00398199, Standard Development of SDV Software Framework for Intelligent Convergence Services). Authors' Addresses Byoungman Robert An (editor) Intelligent Information R and D Division Mobility Platform Research Center 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 An, et al. Expires 6 May 2027 [Page 37] Internet-Draft Agentic AI Framework for SDVs in C-ITS November 2026 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 Pusik Park Intelligent Information R and D Division Mobility Platform Research Center 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 7507 Email: pusik.park@keti.re.kr URI: https://www.keti.re.kr/eng/main/main.php Soohyun Jang Intelligent Information R and D Division Mobility Platform Research Center 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 7436 Email: shjang@keti.re.kr URI: https://www.keti.re.kr/eng/main/main.php An, et al. Expires 6 May 2027 [Page 38]