Internet-Draft Gap Analysis for Agent Protocol November 2025
Mao, et al. Expires 5 May 2026 [Page]
Workgroup:
Network Working Group
Internet-Draft:
draft-mao-rtgwg-agent-comm-protocol-gap-analysis-00
Published:
Intended Status:
Standards Track
Expires:
Authors:
J. Mao
Huawei Technologies
G. Zeng
Huawei Technologies
B. Liu
Huawei Technologies
N. Geng
Huawei Technologies
X. Shang
Huawei Technologies
Q. Gao
Huawei Technologies
Z. Li
Huawei Technologies

Gap Analysis for the Cross-device Communication Protocol for AI Agents in Network Devices

Abstract

With the development of large language models (LLM), AI Agent software continues to emerge. AI agents deployed on different network devices need to collaborate to accomplish some complex tasks, such as network measurement and network troubleshooting. This collaboration requires cross-device communication between AI agents. The cross-device communication framework is defined in [I-D.mzsg-rtgwg-agent-cross-device-comm-framework].

This document describes whether some classical protocols in networking area, and some popular ones in AI Agent area can be used for the cross-device interaction of the AI agents in network devices, and analyzes the gaps.

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 5 May 2026.

Table of Contents

1. Introduction

With the development of large language models (LLM), AI Agent software continues to emerge. AI agents deployed on different network devices need to collaborate to accomplish some complex tasks, such as network measurement and network troubleshooting. This collaboration requires cross-device communication between AI agents. The cross-device communication framework is defined in [I-D.mzsg-rtgwg-agent-cross-device-comm-framework]

This document describes whether some classical protocols in networking area, and some popular ones in AI Agent area can be used for the cross-device interaction of the AI agents in network devices, and analyzes the gaps.

Currently, network devices are able to exchange message with each other by some routing protocols (e.g. BGP, IS-IS, OSPF), or some signaling protocol (e.g. GRASP). In addition, they can interact with network controller by NETCONF, RESTCONF and gRPC.

In AI Agent area, some popular protocol is worth considering, such as A2A and MCP.

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 RFC 2119 [RFC2119] RFC 8174 [RFC8174] when, and only when, they appear in all capitals, as shown here.

3. Terminology

A2A: Agent2Agent Protocol [a2a-link]

MCP: Model Context Protocol [mcp-link]

Device agent: The AI agents deployed in a network device.

GRASP: GeneRic Autonomic Signaling Protocol [RFC8990]

4. Existing Protocols Gap Analysis

Currently, network devices are able to exchange message with each other by some routing protocols (e.g. BGP, IS-IS, OSPF), or some signaling protocol (e.g. GRASP). In addition, they can interact with network controller by NETCONF, RESTCONF and gRPC.

In AI Agent area, there are some popular protocols, such as A2A for interaction between agents and MCP for the interaction between agents and outer systems.

4.1. Gap Analysis for A2A Protocol

4.2. Gap Analysis for MCP Protocol

4.3. Gap Analysis for GRASP Protocol

TBD

5. Other Protocols Gap Analysis

There are some classical protocols which have been well supported by network devices. If they are going to be used in the scenario of the interaction of device agents, their mechanisms may need to be enhanced, and some data schemas/models may need to be extended or newly defined.

On the other hand, if network devices have basic natural language understanding capability, the data model may be designed as a semi-structured format.

5.1. Gap Analysis for BGP Protocol

TBD

5.2. Gap Analysis for IS-IS Protocol

TBD

5.3. Gap Analysis for OSPF Protocol

TBD

5.4. Gap Analysis for NETCONF Protocol

TBD

5.5. Gap Analysis for RESTCONF Protocol

TBD

5.6. Gap Analysis for gRPC Protocol

TBD

6. IANA Considerations

This document does not include an IANA request.

7. Security Considerations

TBD

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, , <https://www.rfc-editor.org/info/rfc2119>.
[RFC8126]
Cotton, M., Leiba, B., and T. Narten, "Guidelines for Writing an IANA Considerations Section in RFCs", BCP 26, RFC 8126, DOI 10.17487/RFC8126, , <https://www.rfc-editor.org/info/rfc8126>.
[RFC8174]
Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC 2119 Key Words", BCP 14, RFC 8174, DOI 10.17487/RFC8174, , <https://www.rfc-editor.org/info/rfc8174>.

8.2. Informative References

"Agent2Agent Protocol", , <https://a2a-protocol.org/>.
[I-D.mzsg-rtgwg-agent-cross-device-comm-framework]
Mao, J., Zeng, G., Liu, B., Geng, N., Shang, X., Gao, Q., and Z. Li, "Cross-device Communication Framework for AI Agents in Network Devices", Work in Progress, Internet-Draft, draft-mzsg-rtgwg-agent-cross-device-comm-framework-01, , <https://datatracker.ietf.org/doc/html/draft-mzsg-rtgwg-agent-cross-device-comm-framework-01>.
"Model Context Protocol", , <https://modelcontextprotocol.io/>.
[RFC8990]
Bormann, C., Carpenter, B., Ed., and B. Liu, Ed., "GeneRic Autonomic Signaling Protocol (GRASP)", RFC 8990, DOI 10.17487/RFC8990, , <https://www.rfc-editor.org/info/rfc8990>.

Authors' Addresses

Jianwei Mao
Huawei Technologies
Beijing
100095
China
Guanming Zeng
Huawei Technologies
Bing Liu
Huawei Technologies
Nan Geng
Huawei Technologies
Xiaotong Shang
Huawei Technologies
Qiangzhou Gao
Huawei Technologies
Zhenbin Li
Huawei Technologies