DMSC Working Group Y. Wang
Internet-Draft A. Wang
Intended status: Standards Track China Telecom
Expires: 19 February 2027 18 August 2026
Distributed Onboarding and Information Synchronization of Agent
Capabilities
draft-wang-dmsc-drisac-01
Abstract
AI Agents may dynamically join, leave, and update their capabilities
while participating in interactions across administrative domains.
Efficient capability discovery in such environments requires
mechanisms to onboard agent capabilities and maintain consistent
capability information across distributed management entities.
Existing service registration and discovery mechanisms do not
necessarily provide a capability-oriented mechanism for distributed
synchronization and hierarchical forwarding of agent capability
information.
This document proposes a distributed and hierarchical mechanism for
AI Agent capability onboarding, information synchronization, and
capability-based discovery. The mechanism introduces a hierarchical
capability classification model and defines two functional entities:
the Agent Capability Management Server (ACMS), which maintains and
synchronizes capability information, and the Agent Capability Access
Server (ACAS), which manages locally attached agents. Capability
information is aggregated and propagated among ACMSs, while access
information for locally attached agents is maintained by ACASs. A
capability table is used to determine forwarding toward relevant
ACMSs, and an access mapping table is used for local agent matching.
The document also describes onboarding and intent-driven capability
discovery procedures. The mechanism is intended to provide a
distributed control-plane foundation for capability-aware agent
discovery and does not define agent-to-agent interaction or task
execution protocols.
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/.
Wang & Wang Expires 19 February 2027 [Page 1]
Internet-Draft Abbreviated-Title August 2026
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 19 February 2027.
Copyright Notice
Copyright (c) 2026 IETF Trust and the persons identified as the
document authors. All rights reserved.
This document is subject to BCP 78 and the IETF Trust's Legal
Provisions Relating to IETF Documents (https://trustee.ietf.org/
license-info) in effect on the date of publication of this document.
Please review these documents carefully, as they describe your rights
and restrictions with respect to this document. Code Components
extracted from this document must include Revised BSD License text as
described in Section 4.e of the Trust Legal Provisions and are
provided without warranty as described in the Revised BSD License.
Table of Contents
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 2
2. Terminology . . . . . . . . . . . . . . . . . . . . . . . . . 3
3. Problem Statement and Design Goals . . . . . . . . . . . . . 3
4. Hierarchical Representation of Capability Classification . . 4
5. Core Entities and Data Structures . . . . . . . . . . . . . . 4
5.1. Capability Table . . . . . . . . . . . . . . . . . . . . 5
5.2. Access Mapping Table . . . . . . . . . . . . . . . . . . 5
6. Distributed Capability Onboarding Procedure . . . . . . . . . 6
7. Intent-Driven Capability Discovery Procedure . . . . . . . . 7
8. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 7
9. Security Considerations . . . . . . . . . . . . . . . . . . . 7
10. Acknowledgements . . . . . . . . . . . . . . . . . . . . . . 7
11. Normative References . . . . . . . . . . . . . . . . . . . . 7
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 8
1. Introduction
AI systems are evolving from task-specific applications toward
autonomous agents capable of perception, reasoning, and action
execution. In this paradigm, agents are expected to communicate,
collaborate, and invoke each other's capabilities across network
administrative domains to accomplish complex tasks. Consequently,
capability onboarding and discovery become fundamental functions for
enabling agent interoperability.
Wang & Wang Expires 19 February 2027 [Page 2]
Internet-Draft Abbreviated-Title August 2026
Existing service registration and discovery mechanisms provide
mechanisms for publishing and locating service instances, but they do
not necessarily provide a distributed, capability-oriented model for
representing and synchronizing the dynamically changing capabilities
of AI Agents across administrative domains.
This document defines a distributed mechanism for hierarchical
capability onboarding and semantic-based capability discovery for AI
Agents. The mechanism provides a scalable foundation for capability-
aware request forwarding and agent selection without modifying the
underlying network infrastructure.
2. Terminology
The following terms are defined in this draft:s
* Agent Capability Type:The basic subdivision unit in the
hierarchical capability classification system, which identifies a
specific functional category that an agent is able to provide.
* Agent Capability Vector: A structured representation of one or
more capability types associated with an AI Agent.
* Agent ID: A globally unique identifier representing a callable AI
Agent instance.
* ACMS: Agent capability management server that manages one or more
types of capabilities. ACMS forms the capabilities table via
exchanging and synchronizing their summarized capabilities tables.
* ACAS: Agent capability access server that provides the attachment
point for AI Agents and maintains information about locally
attached agents and their capabilities.
* Capability Table: A table maintained by ACMSs that maps capability
vectors to next-hop capability servers.
* Access Mapping Table: A table maintained by ACASs that maps
connected agents to their Agent IDs and capability types.
3. Problem Statement and Design Goals
AI systems are evolving from traditional service-oriented
applications toward autonomous agents capable of dynamically
providing, consuming, and composing capabilities. Unlike
conventional service instances, AI Agents continuously join and leave
the network, update their capabilities, and participate in dynamic
collaboration relationships. Existing registration and discovery
Wang & Wang Expires 19 February 2027 [Page 3]
Internet-Draft Abbreviated-Title August 2026
mechanisms are primarily designed for relatively static service
environments. Such mechanisms do not adequately address the
scalability, capability dynamics, and semantic diversity introduced
by large-scale AI Agent deployments. As the number of participating
agents increases, centralized onboarding architectures may become
bottlenecks for capability management and discovery.
Therefore, a capability onboarding mechanism is required to support
scalable capability onboarding, distributed information
synchronization, efficient capability discovery, and dynamic
management of AI Agent capabilities in open network environments.
4. Hierarchical Representation of Capability Classification
Agent capabilities are represented using a hierarchical
classification model as shown in Figure 1. The multi-level
capability tree organizes capabilities from coarse-grained capability
classes to progressively finer-grained subordinate capability
classes. The hierarchy is extensible and allows new capability
classes to be introduced without affecting existing classifications.
[ Agent Capabilities ]
|
+--------------+ . . .
| |
[ Parent Capability [ Parent Capability ------- (Parent Capability Class)
Class A ] Class B ] (Extensible as needed)
|
+--------+--------+ . . . +--------+
| | |
[ Subordinate [ Subordinate [ Subordinate ] --- (Level 1 Subordinate Class)
Class A1 ] Class A2 ] Class An ] (Extensible as needed)
|
+----+ . . . +------+ . . .
| |
[ Subordinate [ Subordinate ] ---------------- (Level 2 Subordinate Class)
Class A1-1 ] Class A1-n ] (Extensible as needed)
:
:
+--------+ . . . +--------+ . . .
| | | |
[ Subordinate [ Subordinate ] ---------------- (Level N Subordinate Class)
Class A1-1...1] Class A1-1...n] (Extensible as needed)
Figure 1 Multi-level Capability Tree Architecture
5. Core Entities and Data Structures
Wang & Wang Expires 19 February 2027 [Page 4]
Internet-Draft Abbreviated-Title August 2026
5.1. Capability Table
A Capability Table is maintained by each ACMS to determine the next-
hop ACMS for capability-related requests. Each table entry
associates a target capability type with one or more next-hop ACMSs.
Each entry consists of a target capability type and the corresponding
next-hop ACMS.
For illustration purposes, consider ACMS responsible for Capability
A.the capability table it maintains is presented in a similar form as
shown in Table 1:
Table 1 Capability Table of ACMS responsible for Capability A
| Target Capability Type | Next-Hop ACMS |
| A | - |
| B | B |
| C | B/D |
| D | D |
Capability tables are constructed based on inter-ACMS connectivity
and are synchronized dynamically. Capability Tables are constructed
as follows:
* ACMSs may establish logical adjacencies through configured or
otherwise established inter-ACMS relationships.
* Each ACMS advertises the capability types for which it is
responsible.
* Capability entries are generated based on the exchanged
advertisements.
5.2. Access Mapping Table
An Access Mapping Table is maintained by each ACAS to record the
association between locally attached AI Agents and their
corresponding Agent IDs. The table enables local capability matching
during the capability discovery procedure.Each entry includes: agent
ID, capability types,and access link identifier.
For illustration purposes, consider a general ACAS maintains the
access mapping table as shown in Table 2:
Wang & Wang Expires 19 February 2027 [Page 5]
Internet-Draft Abbreviated-Title August 2026
Table 2 Access Mapping Table of general ACAS
| Agent | Access Link ID | Agent ID | Agent Capability Type |
| 1 | Physical Port Number | AID-001 | D |
| 2 | VLAN ID | AID-002 | B2, A |
| 3 | VXLAN VNI | AID-003 | B2, C |
| 4 | MPLS Label | AID-004 | E |
| 5 | SRv6 SID | AID-005 | F |
The access link identifier distinguishes all available agents
directly connected to this access server, enabling efficient matching
of locally attached agents according to capability requirements in
the capability discovery process.
6. Distributed Capability Onboarding Procedure
A distributed and hierarchical capability onboarding mechanism is
defined. An AI Agent onboards to an ACAS which aggregate and
propagate agent information to distributed ACMSs based on its local
Access Mapping Table. ACAS subsequently advertises its agent
information toward the corresponding ACMS. The capability onboarding
procedure consists of the following steps:
1. An AI Agent onboards to an ACAS and sends a capability onboarding
request, including capability types and agent ID, to the attached
ACAS. The ACAS records the received information in its Access
Mapping Table
2. The ACAS summarizes onboardings belonging to the same capability
type. The summarized information is propagated toward the
responsible ACMS.
3. The ACAS forwards summarized information toward the target ACMS
according to the capability table.
4. The target ACMS authenticates and confirms the onboarding.
5. An onboarding success response (or Onboarding ACK) is returned.
The ACMS relays onboarding information based on the capability table.
When the ACAS directly connected to an agent happens to be the
agent's target ACMS, capability onboarding is completed directly on
that ACMS. Otherwise, the target management server have to be
located according to the capability table.
Wang & Wang Expires 19 February 2027 [Page 6]
Internet-Draft Abbreviated-Title August 2026
7. Intent-Driven Capability Discovery Procedure
Capability discovery is initiated according to the capability
requirements derived from a task intent. An AI agent issues a
discovery query that is forwarded based on capability classification
using the capability table, enabling location and matching of agents
with required capability types. ACMSs synchronize summarized
capability information and provide capability-based forwarding for
discovery requests. The intent-driven capability discovery mechanism
is as follows:
1. A requester submits a task intent to the service domain, and the
client-side AI Agent attaches to an ingress ACMS.
2. The ingress ACMS maps intent to capability vector and determines
the next-hop ACMS according to the capability table. It
initiates an agent query locally and determines whether the
destination ACAS is directly reachable; otherwise, the request is
forwarded according to the capability table.
3. The ACMS sends an agent query request to the target ACAS.
4. The target ACAS performs local matching according to the access
mapping table.
5. The ACAS returns the matching results (i.e., a list of Agent IDs
of all available agents) to the requesting ACMS, which then
returns the matching Agent IDs to the requesting entity.
8. IANA Considerations
This document makes no request of IANA.
9. Security Considerations
Authentication between agents, ACASs, and ACMSs is REQUIRED.
Capability advertisements SHOULD be integrity-protected. Access
control policies MUST be enforced at onboarding and discovery stages.
10. Acknowledgements
TBD
11. Normative References
Wang & Wang Expires 19 February 2027 [Page 7]
Internet-Draft Abbreviated-Title August 2026
[draft-li-dmsc-macp-05]
L, B., "Gateway Requirements for Dynamic Multi-agents
Secured Collaboration. draft-liu-dmsc-gw-requirements.
", 16 January 2026.
[draft-sz-dmsc-iaip]
S, S., "Intent-based Agent Interconnection Protocol at
Agent Gateway. draft-sz-dmsc-iaip.
", 9
February 2026.
[draft-yang-dmsc-ioa-task-protocol]
Y, C., "Internet of Agents Task Protocol (IoA Task
Protocol) for Heterogeneous Agent Collaboration. draft-
yang-dmsc-ioa-task-protocol.
", 14 January 2026.
[draft-zhang-dmsc-gateway-directory-sync]
Z, L., "Gateway Capability Directory and Synchronization
for Internet of Agents. draft-zhang-dmsc-gateway-
directory-sync. ", 28 April 2026.
[draft-zhang-dmsc-ioa-semantic-interaction]
Z, L., "Ontology-based Semantic Interaction for Internet
of Agents. draft-zhang-dmsc-ioa-semantic-interaction.
", 4 February 2026.
[RFC2119] Bradner, S., "Key words for use in RFCs to Indicate
Requirement Levels", BCP 14, RFC 2119,
DOI 10.17487/RFC2119, March 1997,
.
Authors' Addresses
Yifei Wang
China Telecom
Beiqijia Town, Changping District
Beijing
Beijing, 102209
China
Email: wangyf85@chinatelecom.cn
Wang & Wang Expires 19 February 2027 [Page 8]
Internet-Draft Abbreviated-Title August 2026
Aijun Wang
China Telecom
Beiqijia Town, Changping District
Beijing
Beijing, 102209
China
Email: wangaj3@chinatelecom.cn
Wang & Wang Expires 19 February 2027 [Page 9]