Skip to main content

Agent Gateway Scenario Analysis and Functional Requirements for Cross-Domain Multi-Agent Communication
draft-miao-agw-cross-domain-scenario-analysis-00

Document Type Active Internet-Draft (individual)
Authors Chuanyang Miao , Ran Chen , Jinjie Yan
Last updated 2026-06-26
RFC stream (None)
Intended RFC status (None)
Formats
Stream Stream state (No stream defined)
Consensus boilerplate Unknown
RFC Editor Note (None)
IESG IESG state I-D Exists
Telechat date (None)
Responsible AD (None)
Send notices to (None)
draft-miao-agw-cross-domain-scenario-analysis-00
Network Working Group                                            C. Miao
Internet-Draft                                                   R. Chen
Intended status: Standards Track                                  J. Yan
Expires: 28 December 2026                                ZTE Corporation
                                                            26 June 2026

 Agent Gateway Scenario Analysis and Functional Requirements for Cross-
                    Domain Multi-Agent Communication
            draft-miao-agw-cross-domain-scenario-analysis-00

Abstract

   This document analyzes the communication gaps in three representative
   multi-agent scenarios: single-domain single-agent, single-domain
   multi-agent, and cross-domain multi-agent.  For each scenario, it
   examines whether an Agent Gateway is needed, what capabilities it
   should provide, and where it should be deployed.  Based on the
   consolidated gap analysis, this document derives a set of universal
   functional requirements for the Agent Gateway as a standardized
   cross-domain trust boundary and protocol termination layer.  The
   findings aim to guide the design of interoperable agent communication
   infrastructure.

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 28 December 2026.

Copyright Notice

   Copyright (c) 2026 IETF Trust and the persons identified as the
   document authors.  All rights reserved.

Miao, et al.            Expires 28 December 2026                [Page 1]
Internet-Draft  Agent Gateway Scenario Analysis and Func       June 2026

   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.  Conventions Used in This Document . . . . . . . . . . . . . .   3
     2.1.  Abbreviations . . . . . . . . . . . . . . . . . . . . . .   3
     2.2.  Requirements Language . . . . . . . . . . . . . . . . . .   3
   3.  Scenario Analysis and Gap Identification  . . . . . . . . . .   4
     3.1.  Scenario 1: Single-Domain Single-Agent (1 Agent + Multiple
           Nodes)  . . . . . . . . . . . . . . . . . . . . . . . . .   4
       3.1.1.  Use Case Description  . . . . . . . . . . . . . . . .   4
       3.1.2.  Is an Agent Gateway Needed  . . . . . . . . . . . . .   4
       3.1.3.  Gaps in Current Solutions . . . . . . . . . . . . . .   4
     3.2.  Scenario 2: Single-Domain Multi-Agent (Multiple Agents
           Within One Domain)  . . . . . . . . . . . . . . . . . . .   5
       3.2.1.  Use Case Description  . . . . . . . . . . . . . . . .   5
       3.2.2.  Is an Agent Gateway Needed  . . . . . . . . . . . . .   5
       3.2.3.  Required Capabilities . . . . . . . . . . . . . . . .   6
       3.2.4.  Deployment Location . . . . . . . . . . . . . . . . .   6
       3.2.5.  Gaps in Current Solutions . . . . . . . . . . . . . .   6
     3.3.  Scenario 3: Cross-Domain Multi-Agent Communication  . . .   7
       3.3.1.  Use Case Description  . . . . . . . . . . . . . . . .   7
       3.3.2.  Is an Agent Gateway Needed  . . . . . . . . . . . . .   7
       3.3.3.  Required Capabilities . . . . . . . . . . . . . . . .   7
       3.3.4.  Deployment Location . . . . . . . . . . . . . . . . .   8
       3.3.5.  Gaps in Current Solutions . . . . . . . . . . . . . .   8
   4.  Consolidated Gap Analysis . . . . . . . . . . . . . . . . . .   9
     4.1.  Core Functions  . . . . . . . . . . . . . . . . . . . . .   9
     4.2.  Optional Functions  . . . . . . . . . . . . . . . . . . .  10
     4.3.  Deployment Recommendations  . . . . . . . . . . . . . . .  11
   5.  Security Considerations . . . . . . . . . . . . . . . . . . .  11
   6.  Acknowledgements  . . . . . . . . . . . . . . . . . . . . . .  12
   7.  IANA Considerations . . . . . . . . . . . . . . . . . . . . .  12
   8.  References  . . . . . . . . . . . . . . . . . . . . . . . . .  12
     8.1.  Normative References  . . . . . . . . . . . . . . . . . .  12
     8.2.  Informative References  . . . . . . . . . . . . . . . . .  12
   Authors' Addresses  . . . . . . . . . . . . . . . . . . . . . . .  12

Miao, et al.            Expires 28 December 2026                [Page 2]
Internet-Draft  Agent Gateway Scenario Analysis and Func       June 2026

1.  Introduction

   As agent technology evolves from single-device intelligence to multi-
   device collaboration and cross-domain interconnection, there is a
   growing demand for multi-agent communication across home, vehicle,
   and enterprise campus scenarios.  Typical use cases include:

   *  Multiple sub-agents (lighting, security, HVAC) within a home
      collaborating to execute an "arrive home" scene;

   *  A vehicle agent communicating with a user home agent across
      domains to enable "auto-arm when leaving, pre-condition when
      approaching";

   *  Agents from different vendors (e.g., User Home Agent and 3rd-party
      Vehicle Agent) needing to cooperate across trust domains.

   However, current agent communication architectures lack a
   standardized cross-domain trust boundary and protocol termination
   layer.  This document aims to analyze three representative scenarios
   (single-domain single-agent, single-domain multi-agent, and cross-
   domain multi-agent), identify gaps in existing solutions, and argue
   for the necessity, capability requirements, and deployment options of
   an Agent Gateway as a universal infrastructure component.

2.  Conventions Used in This Document

2.1.  Abbreviations

   *  AGW: Agent Gateway

   *  HITL: Human-in-the-loop

   *  HVAC: Heating, Ventilation and Air Conditioning

2.2.  Requirements Language

   The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
   "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and
   "OPTIONAL" in this document are to be interpreted as described in BCP
   14 [RFC2119] [RFC8174] when, and only when, they appear in all
   capitals, as shown here.

Miao, et al.            Expires 28 December 2026                [Page 3]
Internet-Draft  Agent Gateway Scenario Analysis and Func       June 2026

3.  Scenario Analysis and Gap Identification

3.1.  Scenario 1: Single-Domain Single-Agent (1 Agent + Multiple Nodes)

3.1.1.  Use Case Description

   A home has a single Agent managing multiple smart devices (physical
   nodes).  For example:

   *  A central hub (Node A) runs the Supervisor Agent;

   *  A smart speaker (Node B) serves as the voice interaction
      interface;

   *  A ZigBee gateway (Node C) connects ZigBee lights and sensors.

   The Supervisor Agent communicates with each node via a soft bus
   (e.g., DSoftBus, local MQTT) and provides a unified service
   externally.  Users issue commands via voice or app; the Supervisor
   Agent parses the intent and dispatches tasks to the appropriate node.
   Naturally, if all household devices are assigned IP addresses, a mesh
   network can be established over the home network.  Furthermore, the
   aforementioned devices can communicate directly via peer-to-peer
   (P2P) protocols.

3.1.2.  Is an Agent Gateway Needed

   No.  In this scenario, all communication occurs within the same trust
   domain (home LAN).  The Supervisor Agent can interact directly with
   each node.  There is no cross-domain security boundary.  External
   access (e.g., mobile app) typically goes through the vendor cloud,
   which is outside the scope of Agent Gateway.

3.1.3.  Gaps in Current Solutions

Miao, et al.            Expires 28 December 2026                [Page 4]
Internet-Draft  Agent Gateway Scenario Analysis and Func       June 2026

*-------------------------------------------------------------------------*
|      Issue              |                Description                    |
*-------------------------*-----------------------------------------------*
| Lack of standardized    |The Supervisor Agent's capabilities (Skills)   |
| external interface      |have no standard way to be exposed externally; |
|                         |apps must use vendor-specific private APIs     |
*-------------------------*-----------------------------------------------*
| Node discovery and      |Nodes register via soft bus, but registration  |
| registration rely on    |format and heartbeat mechanisms are            |
| proprietary protocols   |non-standard                                   |
*-------------------------*-----------------------------------------------*
| Insufficient offline    |Some solutions rely on cloud-based intent      |
| autonomy                |parsing, degrading local orchestration         |
|                         |when disconnected                              |
*-------------------------*-----------------------------------------------*

   Note: Gaps in this scenario are more about "external exposure" and
   "standardization," but introducing an Agent Gateway is not strictly
   necessary; these gaps could be addressed by enhancing the Supervisor
   Agent itself.

3.2.  Scenario 2: Single-Domain Multi-Agent (Multiple Agents Within One
      Domain)

3.2.1.  Use Case Description

   A home contains multiple independent agents, each managing a
   different subsystem, requiring inter-operation.  For example:

   *  Lighting Agent: manages all lighting devices;

   *  Security Agent: manages door locks, cameras, alarms;

   *  Environment Agent: manages HVAC, curtains, air purifiers.

   These agents may run on different hardware nodes (central hub, smart
   speaker, dedicated gateway).  They need to discover each other's
   capabilities, subscribe to events, and collaboratively execute scenes
   (e.g., "away mode": Security Agent arms, Lighting Agent turns off
   lights, Environment Agent switches to energy-saving mode).

3.2.2.  Is an Agent Gateway Needed

   Yes, but with a different role than in the cross-domain scenario.
   Here, the Agent Gateway should act as an intra-domain registry and
   task routing layer, rather than a cross-domain security boundary.

Miao, et al.            Expires 28 December 2026                [Page 5]
Internet-Draft  Agent Gateway Scenario Analysis and Func       June 2026

3.2.3.  Required Capabilities

   *  Intra-domain Agent Card Registration and Discovery: Each agent
      registers its Skills and capability description (Agent Card) with
      the Gateway; the Gateway maintains a domain-wide capability index.

   *  Intra-domain Task Routing: When Agent A needs to invoke a Skill of
      Agent B, the request goes through the Gateway, which handles
      addressing and optional load balancing.

   *  Event Bus: Support publish/subscribe model so agents can subscribe
      to events from other agents (e.g., security alarm triggered ��
      lighting turns on).

   *  Local-first: All communication should complete within the LAN,
      without depending on public internet connectivity.

3.2.4.  Deployment Location

   *  Standalone device: e.g., home central hub, NAS, or high-
      performance router.

   *  Collocated with Supervisor Agent: If the domain has a single
      Supervisor Agent managing all sub-agents, it can also serve as the
      Gateway.

3.2.5.  Gaps in Current Solutions

*-------------------------*-----------------------------------------------*
|      Issue              |                Description                    |
*-------------------------*-----------------------------------------------*
| No standard inter-agent |Agents discover each other via proprietary     |
| discovery               |soft bus or hardcoded addresses; no unified    |
|                         |registry                                       |
*-------------------------*-----------------------------------------------*
| Task routing depends on |Agent A must know Agent B's address and        |
| point-to-point          |protocol,creating tight coupling               |
| connections             |                                               |
*-------------------------*-----------------------------------------------*
| No standardized event   |Event formats and subscription mechanisms      |
| subscription            |vary across vendors, hindering cross-brand     |
|                         |collaboration                                  |
*-------------------------*-----------------------------------------------*
| Unclear intra-domain    |No unified authentication between agents; a    |
| security boundary       |malicious agent could impersonate another      |
*-------------------------*-----------------------------------------------*

Miao, et al.            Expires 28 December 2026                [Page 6]
Internet-Draft  Agent Gateway Scenario Analysis and Func       June 2026

3.3.  Scenario 3: Cross-Domain Multi-Agent Communication

3.3.1.  Use Case Description

   Two or more agents from different trust domains need to communicate
   across domain boundaries.  Typical use cases:

   *  Home Domain <-> Vehicle Domain: As the owner drives home, the
      vehicle agent sends an "estimated arrival in 10 minutes" event to
      the home agent, which pre-conditions the HVAC, turns on lights,
      and disarms the security system.

   *  Home Domain <-> Cloud LLM Agent: A user queries home status or
      issues commands via a cloud-based LLM agent, which invokes Skills
      exposed by the home agent.

   *  Home Domain A <-> Home Domain B (neighbor assistance): Neighbor
      A's security agent detects an anomaly and notifies neighbor B's
      security agent to increase vigilance.

3.3.2.  Is an Agent Gateway Needed

   Strongly needed.  Cross-domain scenarios face fundamental challenges
   including NAT traversal, trust establishment, protocol translation,
   and information hiding.  An Agent Gateway is an essential cross-
   domain trust boundary and protocol termination layer.

3.3.3.  Required Capabilities

   *  External A2A Endpoint: Expose standardized endpoints, such as for
      /.well-known/agent.json and POST /a2a/tasks, supporting HTTP/
      HTTPS.

   *  Authentication and Authorization: for example, Support OAuth2
      Device Flow, JWT issuance and verification, and Scope
      whitelisting.

   *  Aggregated Agent Card: Merge all intra-domain Skills into a single
      Card for external exposure, hiding internal topology.

   *  Reverse Channel Management: Accept reverse WebSocket/MQTT
      connections from the intra-domain Supervisor Agent for task
      dispatch and artifact return.

   *  Cross-domain Federation: Establish mutual trust with Gateways in
      other domains, exchange aggregated Cards, and enable cross-domain
      discovery and Task Proxy.

Miao, et al.            Expires 28 December 2026                [Page 7]
Internet-Draft  Agent Gateway Scenario Analysis and Func       June 2026

   *  HITL (Human-in-the-Loop): For high-risk Skills (e.g., unlock
      door), support suspending the Task and pushing a confirmation
      request to the user's app.

   *  Audit Logging: Record the full chain of cross-domain calls
      (issuer, skill_id, status, timestamp).

3.3.4.  Deployment Location

   *  Home network edge: Deployed on the home gateway (router/ONT) or a
      standalone edge computing device, serving as the sole external
      entry point for the home domain.

   *  Cloud: If the home lacks public reachability, deploy on the vendor
      cloud as a Relay Gateway; the home Supervisor Agent connects via a
      reverse channel.

   *  Hybrid mode: Cloud Gateway acts as global Registry and Auth
      Broker; Edge Gateway performs local A2A termination (when publicly
      reachable).

3.3.5.  Gaps in Current Solutions

Miao, et al.            Expires 28 December 2026                [Page 8]
Internet-Draft  Agent Gateway Scenario Analysis and Func       June 2026

*-------------------------*-----------------------------------------------*
|      Issue              |                Description                    |
*-------------------------*-----------------------------------------------*
| Cross-domain discoverye |mDNS/BLE limited to LAN; cloud-to-cloud        |
| unavailable             |integration costly; no standardized Agent      |
|                         |Card format                                    |
*-------------------------*-----------------------------------------------*
| No standard NAT         |Direct connection requires public IP/DDNS;     |
| traversal solution      |reverse channel protocols are proprietary      |
*-------------------------*-----------------------------------------------*
| No standardized event   |Event formats and subscription mechanisms      |
| subscription            |vary across vendors, hindering cross-brand     |
|                         |collaboration                                  |
*-------------------------*-----------------------------------------------*
| Cross-domain trust      |No unified Federation trust bootstrap process; |
| establishment is        |Scope models inconsistent                      |
| difficult               |                                               |
*-------------------------*-----------------------------------------------*
| No standard HITL        |Actions like unlocking doors lack a            |
| mechanism for high-risk |standardized human-in-the-loop confirmation    |
| operations              |workflow                                       |
*-------------------------*-----------------------------------------------*
| No cross-domain         |External agents require multiple protocol      |
| semantics for task      |translations to reach the target sub-agent     |
| routing                 |                                               |
*-------------------------*-----------------------------------------------*
| Audit logs scattered    |Cross-domain call chains cannot be traced      |
|                         |end-to-end                                     |
*-------------------------*-----------------------------------------------*

4.  Consolidated Gap Analysis

   Based on the analysis of the three scenarios above, common gaps
   across current agent communication architectures can be summarized as
   follows:

4.1.  Core Functions

Miao, et al.            Expires 28 December 2026                [Page 9]
Internet-Draft  Agent Gateway Scenario Analysis and Func       June 2026

*-------------------------*-----------------------------------------------*-------------*
|      Function           |                Description                    | Applicable  |
|                         |                                               | Scenarios   |
*-------------------------*-----------------------------------------------*-------------*
| Agent Card Registration |Receive capability registrations from          |             |
| & Aggregation           |intra-domain agents; merge into an aggregated  |2, 3         |
|                         |Card; expose via standardized endpoint         |             |
*-------------------------*-----------------------------------------------*-------------*
| A2A Protocol Termination|Support standard A2A Task interface (POST      |             |
|                         |/a2a/tasks); translate external requests into  |3            |
|                         |internal commands                              |             |
*-------------------------*-----------------------------------------------*-------------*
| Authentication &        |Support JWT/OAuth2; verify caller identity and |3 (optional  |
| Authorization           |Scope whitelist                                |for 2)       |
*-------------------------*-----------------------------------------------*-------------*
| Reverse Channel         |Accept reverse WebSocket/MQTT connections from |             |
| Management              |intra-domain Supervisor Agent for task dispatch|3            |
*-------------------------*-----------------------------------------------*-------------*
| Task Routing            |Route Tasks to the correct intra-domain agent  |             |
|                         |or cross-domain Gateway based on Skill ID      |2, 3         |
*-------------------------*-----------------------------------------------*-------------*
| Information Hiding      |Do not expose sub-agent count, IP addresses,   |             |
|                         |protocols, or other internal details externally|3            |
*-------------------------*-----------------------------------------------*-------------*
| HITL Trigger            |Mark high-risk Skills with                     |             |
|                         |require_human_approval; suspend Task and wait  |3            |
|                         |for user confirmation                          |             |
*-------------------------*-----------------------------------------------*-------------*
| Audit logging           |Record full chain of cross-domain calls        |3            |
*-------------------------*-----------------------------------------------*-------------*

   Core conclusion: As agents evolve from single-node to multi-node and
   from intra-domain to cross-domain operation, the lack of a
   standardized trust boundary and protocol termination layer has become
   a primary bottleneck.  The Agent Gateway is the key infrastructure
   component to fill this gap.

4.2.  Optional Functions

Miao, et al.            Expires 28 December 2026               [Page 10]
Internet-Draft  Agent Gateway Scenario Analysis and Func       June 2026

*-------------------------*-----------------------------------------------*-------------*
|      Function           |                Description                    | Applicable  |
|                         |                                               | Scenarios   |
*-------------------------*-----------------------------------------------*-------------*
| Intra-domain Event Bus  |Support publish/subscribe between intra-domain |             |
|                         |agents                                         |2            |
*-------------------------*-----------------------------------------------*-------------*
| Federation              |Exchange aggregated Cards with other domain    |             |
| Synchronization         |Gateways for cross-domain discovery            |3            |
*-------------------------*-----------------------------------------------*-------------*
| Local Caching & Offline |Cache aggregated Cards and authorization       |             |
| Autonomy                |policies; handle authorized local Tasks when   |2, 3         |
|                         |disconnected                                   |             |
*-------------------------*-----------------------------------------------*-------------*

4.3.  Deployment Recommendations

   *  Single-domain multi-agent scenario: The Agent Gateway can be
      deployed on an intra-domain central hub device, collocated with or
      separate from the Supervisor Agent.

   *  Cross-domain multi-agent scenario: The Agent Gateway should be
      deployed at the home network edge or in the vendor cloud, serving
      as the sole external entry point.

   *  Hybrid deployment: Cloud Gateway acts as global Registry and Auth
      Broker; Edge Gateway performs local A2A termination, balancing
      reachability and low latency.

5.  Security Considerations

   The Agent Gateway, as the sole entry point for cross-domain
   communication, must enforce strict security measures:

   *  All external interfaces MUST use TLS 1.3 encryption.

   *  Authentication tokens SHOULD have a limited validity period
      (recommended no more than 24 hours) and support refresh.

   *  Cross-domain requests MUST pass mTLS or Federation-level cascading
      trust verification.

   *  Highly sensitive operations (e.g., door lock control) MUST enable
      the HITL mechanism, and HITL confirmation requests SHOULD be
      delivered to the user through an independent channel (e.g., mobile
      push notification).

Miao, et al.            Expires 28 December 2026               [Page 11]
Internet-Draft  Agent Gateway Scenario Analysis and Func       June 2026

   *  All gateway components SHOULD record complete audit logs,
      including request source, target, operation, result, and
      timestamp.  Logs MUST be tamper-proof.

6.  Acknowledgements

   TBA.

7.  IANA Considerations

   TBA.

8.  References

8.1.  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,
              <https://www.rfc-editor.org/rfc/rfc2119>.

   [RFC8174]  Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC
              2119 Key Words", BCP 14, RFC 8174, DOI 10.17487/RFC8174,
              May 2017, <https://www.rfc-editor.org/rfc/rfc8174>.

8.2.  Informative References

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

   [RFC7519]  Jones, M., Bradley, J., and N. Sakimura, "JSON Web Token
              (JWT)", RFC 7519, DOI 10.17487/RFC7519, May 2015,
              <https://www.rfc-editor.org/rfc/rfc7519>.

   [RFC8446]  Rescorla, E., "The Transport Layer Security (TLS) Protocol
              Version 1.3", RFC 8446, DOI 10.17487/RFC8446, August 2018,
              <https://www.rfc-editor.org/rfc/rfc8446>.

Authors' Addresses

   Chuanyang Miao
   ZTE Corporation
   Email: miao.chuanyang@zte.com.cn

   Ran Chen
   ZTE Corporation

Miao, et al.            Expires 28 December 2026               [Page 12]
Internet-Draft  Agent Gateway Scenario Analysis and Func       June 2026

   Email: chen.ran@zte.com.cn

   Jinjie Yan
   ZTE Corporation
   Email: yan.jinjie@zte.com.cn

Miao, et al.            Expires 28 December 2026               [Page 13]