Task-oriented Coordination Requirements for AI Agent Protocols
draft-cui-ai-agent-task-01
This document is an Internet-Draft (I-D).
Anyone may submit an I-D to the IETF.
This I-D is not endorsed by the IETF and has no formal standing in the
IETF standards process.
| Document | Type | Active Internet-Draft (individual) | |
|---|---|---|---|
| Authors | Yong Cui , Chenguang Du | ||
| Last updated | 2026-07-03 | ||
| 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-cui-ai-agent-task-01
Network Working Group Y. Cui
Internet-Draft Tsinghua University
Intended status: Informational C. Du
Expires: 4 January 2027 Zhongguancun Laboratory
3 July 2026
Task-oriented Coordination Requirements for AI Agent Protocols
draft-cui-ai-agent-task-01
Abstract
AI agent communication requires intelligent task level coordination
to manage dynamic workloads across large-scale, heterogeneous
networking environments. This draft proposes general requirements
for an agent protocol to enable autonomous task coordination at
scale, including dynamic task discovery, negotiation, and context-
aware scheduling with real-time adaptability.
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 4 January 2027.
Copyright Notice
Copyright (c) 2026 IETF Trust and the persons identified as the
document authors. All rights reserved.
Cui & Du Expires 4 January 2027 [Page 1]
Internet-Draft Agent Task Coordination July 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 . . . . . . . . . . . . . . . . . . . . . . . . 2
1.1. Purpose . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.2. Terminology . . . . . . . . . . . . . . . . . . . . . . . 3
1.3. Task Coordination Framework . . . . . . . . . . . . . . . 3
2. Use Cases . . . . . . . . . . . . . . . . . . . . . . . . . . 4
3. Necessity . . . . . . . . . . . . . . . . . . . . . . . . . . 5
3.1. Task Complexity . . . . . . . . . . . . . . . . . . . . . 5
3.2. Resource Optimization . . . . . . . . . . . . . . . . . . 5
3.3. Quality of Service . . . . . . . . . . . . . . . . . . . 5
3.4. Dynamic Adjustment . . . . . . . . . . . . . . . . . . . 5
4. Protocol Requirements . . . . . . . . . . . . . . . . . . . . 5
4.1. Task Description . . . . . . . . . . . . . . . . . . . . 6
4.2. Task State . . . . . . . . . . . . . . . . . . . . . . . 6
4.3. Context Sharing . . . . . . . . . . . . . . . . . . . . . 7
4.4. Exception Handling . . . . . . . . . . . . . . . . . . . 7
5. The Requirements on the Agent Session Protocol . . . . . . . 7
6. Task Flow . . . . . . . . . . . . . . . . . . . . . . . . . . 8
6.1. Task Operation . . . . . . . . . . . . . . . . . . . . . 8
6.2. Task Parameters . . . . . . . . . . . . . . . . . . . . . 10
7. Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . 10
8. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 11
9. Security Considerations . . . . . . . . . . . . . . . . . . . 11
10. References . . . . . . . . . . . . . . . . . . . . . . . . . 11
10.1. Normative References . . . . . . . . . . . . . . . . . . 11
10.2. Informative References . . . . . . . . . . . . . . . . . 11
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 11
1. Introduction
1.1. Purpose
With the rapid advancements of AI technologies and their
applications, AI agents utilizing Large Language Models (LLMs) have
emerged as a pivotal direction in global technological evolution and
market development. The single-agent systems exhibit inherent
limitations when addressing complex tasks in dynamic environments,
the efficient multi-agent collaboration for complex task completion
Cui & Du Expires 4 January 2027 [Page 2]
Internet-Draft Agent Task Coordination July 2026
has garnered increasing attention, wherein task-oriented coordination
constitutes a critical component of standardized multi-agent systems.
This document examines the requirements and operations for
standardizing AI Agent protocols to support task coordination in
multi-agent systems.
1.2. Terminology
Task:
ISO/IEC 22989, task is actions required to achieve a specific
goal. These actions can be physical or cognitive. For instance,
computing or creation of predictions, translations, synthetic data
or artefacts or navigating through a physical space.
Shared Message Pool:
A pool where agents publish structured messages and subscribe to
relevant messages based on their profiles.
Coordinator Agent:
An agent that receives tasks and decomposes or distributes tasks
to other agents.
Execution Agent:
An agent responsible for executing tasks distributed by the
Coordinator Agent.
Agent Communication Server:
The server enables Agents to communicate and collaborate with each
other, which provides session management, routing function, etc.
Normative Language:
The key words "MUST", "REQUIRED", and "SHOULD" in this document
are to be interpreted as described in [RFC2119].
1.3. Task Coordination Framework
Cui & Du Expires 4 January 2027 [Page 3]
Internet-Draft Agent Task Coordination July 2026
+---------+
+------------------->| Agent X |
|2.Task1 distributed +---------+
| |
| |
| |
+---------+ 1.Task submitted +---------+ 3.Task1 completed|
| Task |------------------->| |<-----------------+
| Invoker |<------------------ | Agent A |<-----------------+
+---------+ 4.Task completed +---------+ 3.Task2 completed|
| |
| |
| |
|2.Task2 distributed +---------+
+------------------->| Agent Y |
+---------+
Figure 1: Task Coordination Framework
The system operates as follows: when a task invoker submits a task to
Agent A (Coordinator), the Agent A SHOULD use the standard discovery
mechanism to discover Agent X and Agent Y that own the required
capabilities and assign tasks to them. Upon receiving completion
notifications from both agents, Agent A aggregates the results and
delivers the final artifact back to the task invoker.
2. Use Cases
Some typical use cases in which multiple agents work together to
complete tasks:
* High throughput tasks: There are many tasks that have high
bandwidth requirements. For example, in the collaborative
framework for coordinating heterogeneous embodied agents-
specifically, the robot dogs and drones-in a wide-area public
network, the drone is assigned for wide-area surveillance and task
delegation, while functionally specialized robot dogs perform
ground-level operations such as video surveillance, material
transport and obstacle clearance.
* Low latency tasks: In collaborative multi-agent systems, control
signal transmission tasks impose significantly more stringent
latency requirements than routine model training data transfer.
For example, the home robot remotely sends an alarm message to the
end user.
Cui & Du Expires 4 January 2027 [Page 4]
Internet-Draft Agent Task Coordination July 2026
* High reliability tasks: Smart factory scenarios require critical
reliability of agent task execution and fault-tolerant operation
stability.
These categories of use cases (may be further extended) demonstrate
the collaboration among agents spanning multiple distinct domains to
achieve end-to-end task completion. The embodied agents (such as the
robots and unmanned aerial vehicles) interacting with physical
environments through embodied interfaces, while virtual agents (such
as the various software applications and personal assistant)
providing complementary capabilities, has demonstrated the advantages
of collaboratively completing complex tasks in various scenarios.
3. Necessity
3.1. Task Complexity
As task complexity increases, heterogeneous agents require multiple
interaction rounds, precise planning, ordered execution, and
efficient context sharing mechanisms to enhance resolution quality
and robustness.
3.2. Resource Optimization
Through task coordination and resource consumption monitoring, the
multi-agent systems are able to support dynamic allocation of for
example, the computing, storage and bandwidth resources to optimize
the resource utilization efficiency.
3.3. Quality of Service
Task coordination may dynamically prioritize resources allocations
based on for example, task priorities, agent expertise and Quality of
Service requirements. This ensures timeliness and accuracy of
critical tasks, reduces service response latency, and maintains
output stability and reliability.
3.4. Dynamic Adjustment
The agents may update or adjust the task during task execution phase
based on end user's inputs or contextual updates to better respond to
the final task requirements.
4. Protocol Requirements
Cui & Du Expires 4 January 2027 [Page 5]
Internet-Draft Agent Task Coordination July 2026
4.1. Task Description
Precise task descriptions or task templates are REQUIRED to ensure
all agents maintain a consistent understanding of the objectives,
operational constraints and criteria.
A well-defined task description:
* Reduces ambiguity: Minimizes misinterpretations and conflicting
actions among agents.
* Enables verifiability: Translates abstract goals into executable
and measurable plans.
* Improves robustness: Ensures collaboration remains coherent and
efficient under dynamic conditions.
The AI Agent protocol should support a structured task description
format. A complete task description may include the following
components:
* Metadata: task identifier, task type (e.g., execution,
monitoring), task priority, creation time, expected completion
time, task initiator, etc.
* Task objective: the objective described in natural language.
* Task execution constraints: the constraints include resource
limitations, safety requirements, etc.
* Task artifact specifications: the expected output format and the
desired artifact list.
Task descriptions assigned to different agents MUST follow the
minimization principle, i.e., agents SHOULD receive only the minimal,
contextually necessary information required to fulfill their tasks to
prevent unauthorized access of sensitive information.
4.2. Task State
The AI Agent protocol design should support comprehensive state
descriptions throughout the task execution lifecycle. The potential
task states may include task submitted, running, suspended (awaiting
external input or output from other agents), completed, canceled,
rejected, and failed, as well as management operations such as state
queries, retrieval, and pushing intermediate results.
Cui & Du Expires 4 January 2027 [Page 6]
Internet-Draft Agent Task Coordination July 2026
Based on the length of time to complete the tasks, tasks can be
categorized into short-term tasks that require a single request-
response interaction and long-term tasks that may require multi-round
interactions or extended waiting periods. For long-term tasks, the
reporting and querying of intermediate states (e.g., progress
percentage, checkpoints) should be supported. The Coordinator Agent
may dynamically adjust the target of the task according to
intermediate results from the Execution Agents and the context
information. The AI Agent protocol design should support management
of both long-term and short-term tasks.
4.3. Context Sharing
When delegating tasks to Execution Agents, the Coordinator Agent may
include task-relevant contextual about the contact information of the
end user, the task itself, the historical preference information
known by the Coordinator Agent, and other necessary conversation
data, to facilitate the task execution. For example, in trip
planning case, this may encompass historically booked flight/hotel
preferences or dynamically perceived context like recent user dialog.
The AI Agent protocol design should consequently support context
sharing mechanisms through standardized definitions of context types,
length constraints, and encoding formats to enhance the effectiveness
of task execution.
The context sharing MAY have an impact on privacy of the user, it is
necessary to consider the limitations of the scope of context
sharing, especially for the sensitive information e.g. name, age,
address of the user.
4.4. Exception Handling
Exception handling constitutes a critical mechanism for multi-agent
collaborative task execution. If an execution agent cannot complete
an assigned task due to lack of skills or overloaded, the failure in
task execution may lead to such as releasing the connections.
5. The Requirements on the Agent Session Protocol
The AI Agent protocol should consider separating the transmission of
task control messages (such as task creation, task update, task
status query and task result notification) from the transmission of
real-time multimodal context (such as task-related voice, video, and
images). These two different types of messages may require different
transmission channels. This AI Agent protocol can be built on top of
the Agent session protocol and make use of the Agent session protocol
to enable the exchange of task control messages, real-time and non-
real-time multimodal context between AI agents with low-latency.
Cui & Du Expires 4 January 2027 [Page 7]
Internet-Draft Agent Task Coordination July 2026
The AI Agent session protocol should be able to provide mechanisms
beyond simple request/response, including the complex interaction
modes for example message multicast, publication/subscription (PUB/
SUB), asynchronous notifications.
6. Task Flow
6.1. Task Operation
After receiving the target agent list from the discovery result, the
Coordinator Agent may select one Execution Agent and send the task
cooperation message to that agent. The Coordinator Agent may
delegate agent identifier lookup to the Agent Communication Server,
which is then responsible for routing the message according to the
agent identifier.
The Agent Communication Server MAY also provide task state management
according to service requirements, for example, retry/re-entry after
task failure.
+-----+ +-------------+ +-----+
| |-(A)task request-->| | | |
| AI | | Agent |-(B)task request-->| AI |
|Agent| |Communication| |Agent|
| A | | Server |<-(C)task response-| B |
| |<-(D)task response-| | | |
+-----+ +-------------+ +-----+
Figure 2: Agent Communication Flow in the Same Domain
Figure 2 shows the abstract task cooperation procedure between agent
A and agent B in the same domain:
(A)
The AI Agent A sends a task request to AI Agent B via the Agent
Communication Server.
(B)
The Agent Communication Server verifies the request message and
routes the request to AI Agent B.
(C)
The AI Agent B receives the task request and sends a response to
the Agent Communication Server.
(D)
The Agent Communication Server transfers the response to AI Agent
A.
Cui & Du Expires 4 January 2027 [Page 8]
Internet-Draft Agent Task Coordination July 2026
+------+ +-------------+
| |-(A)task request-->| |
| AI | | Agent |
| Agent| |Communication|
| A | | Server X |
| |<-(F)task response-| |
+------+ +-------------+
| ^
| |
(B)task request (E)task response
| |
v |
+------+ +-------------+
| |<-(C)task request--| |
| AI | | Agent |
| Agent| |Communication|
| B | | Server Y |
| |-(D)task response->| |
+------+ +-------------+
Figure 3: Agent Communication Flow across Domains
Figure 3 shows the abstract task cooperation procedure between agent
A and agent B across domains:
(A)
The AI Agent A sends a task request to AI Agent B via Agent
Communication Server X.
(B)
Agent Communication Server X verifies the request, parses agent
B's identifier, obtains the routing address of Agent Communication
Server Y, establishes a message channel with Server Y, and routes
the request to Server Y.
(C)
Agent Communication Server Y receives and verifies the task
request message, then routes the request to agent B.
(D)
AI Agent B receives the task request and sends a response to Agent
Communication Server Y.
(E)
Agent Communication Server Y transfers the response to Agent
Communication Server X.
Cui & Du Expires 4 January 2027 [Page 9]
Internet-Draft Agent Task Coordination July 2026
(F)
Agent Communication Server X transfers the response to AI Agent A.
6.2. Task Parameters
The following parameters are included in the agent task cooperation
request:
Message Name
REQUIRED. It specifies the message name.
Agent Identifier
REQUIRED. It specifies the identifier of the Execution Agent.
Task Description
REQUIRED. It specifies the task description that needs to be
completed by the Execution Agent, as defined in Section 4.1.
Input
REQUIRED. It specifies the task input parameters; the input can
be text, file, image, and similar modalities.
Context
OPTIONAL. It specifies context information as defined in
Section 4.3.
The following parameters are included in the agent task cooperation
response:
Task State
REQUIRED. It specifies the task state as defined in Section 4.2.
Output
REQUIRED. It specifies the output result information of the task;
the output can be text, file, image, and similar modalities.
7. Conclusions
Task-oriented coordination constitutes a critical function for multi-
agent collaboration. This document discusses the necessity of
introducing task-oriented coordination to address complex tasks,
optimize resource utilization, and guarantee service quality.
Consequently, it analyzes the requirements imposed by task-oriented
coordination on AI Agent protocol design, specifically concerning
task descriptions, task states, communication mechanisms, context
sharing, and exception handling. Finally, it introduces the task
flow and parameters for task cooperation between Agents.
Cui & Du Expires 4 January 2027 [Page 10]
Internet-Draft Agent Task Coordination July 2026
8. IANA Considerations
This memo includes no request to IANA.
9. Security Considerations
When designing the task-oriented coordination for AI agents
communication, privacy should always be considered.
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,
<https://www.rfc-editor.org/rfc/rfc2119>.
10.2. Informative References
[Multi-Agents]
Guo, T., Chen, X., Wang, Y., Chang, R.i., Pei, S., Chawla,
N.V., Wiest, O., and X. Zhang, "Large Language Model based
Multi-Agents: A Survey of Progress and Challenges", 2024.
[MetaGPT] Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y.,
Zhang, C., Wang, J., Wang, Z., Yau, S., Lin, Z., Zhou, L.,
Ran, C., Xiao, L., Wu, C., and J. Schmidhuber, "MetaGPT:
Meta Programming for A Multi-Agent Collaborative
Framework", 2023.
Authors' Addresses
Yong Cui
Tsinghua University
Beijing, 100084
China
Email: cuiyong@tsinghua.edu.cn
URI: http://www.cuiyong.net/
Chenguang Du
Zhongguancun Laboratory
Beijing, 100094
China
Email: ducg@zgclab.edu.cn
Cui & Du Expires 4 January 2027 [Page 11]