Structured Data Schema Interaction Protocol for Multi-Agent Collaboration
draft-zhou-structured-data-schema-interaction-00
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 | Fangtong Zhou , Shuping Peng | ||
| Last updated | 2026-06-22 | ||
| 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-zhou-structured-data-schema-interaction-00
Working Group F. Zhou
Internet-Draft S. Peng
Intended status: Standards Track Huawei Technologies
Expires: 24 December 2026 22 June 2026
Structured Data Schema Interaction Protocol for Multi-Agent
Collaboration
draft-zhou-structured-data-schema-interaction-00
Abstract
This document defines a structured data schema interaction protocol
for multi-agent collaboration. As AI agents increasingly
interoperate across heterogeneous platforms, natural-language-based
communication suffers from semantic drift, high inference overhead,
and ambiguous data flow. This protocol introduces a standardized
key-value schema with semantic annotations, enabling deterministic,
efficient, and interoperable agent-to-agent communication. A
lightweight schema negotiation mechanism is provided for initial
alignment at the beginning of communication, while an optional key-
value update mechanism allows agents to reflect evolving requirements
without breaking existing structured data schema interaction
protocol.
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 24 December 2026.
Copyright Notice
Copyright (c) 2026 IETF Trust and the persons identified as the
document authors. All rights reserved.
Zhou & Peng Expires 24 December 2026 [Page 1]
Internet-Draft Structured Data Schema Interaction 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
1.1. Requirements Language . . . . . . . . . . . . . . . . . . 4
2. Terminology . . . . . . . . . . . . . . . . . . . . . . . . . 4
3. Protocol Overview . . . . . . . . . . . . . . . . . . . . . . 5
3.1. Interaction Model . . . . . . . . . . . . . . . . . . . . 5
3.2. Message Flow . . . . . . . . . . . . . . . . . . . . . . 5
4. Structured Key-Value Format . . . . . . . . . . . . . . . . . 8
4.1. Schema Template . . . . . . . . . . . . . . . . . . . . . 8
4.2. Semantic Annotation . . . . . . . . . . . . . . . . . . . 10
4.3. The "other" Key . . . . . . . . . . . . . . . . . . . . . 11
5. Illustrations of the protocol . . . . . . . . . . . . . . . . 11
5.1. Flight Booking . . . . . . . . . . . . . . . . . . . . . 11
5.2. Photo Editing . . . . . . . . . . . . . . . . . . . . . . 12
6. Capability Enhancement . . . . . . . . . . . . . . . . . . . 13
6.1. LLM-based Semantic Parsing . . . . . . . . . . . . . . . 14
6.2. Key-Value Schema Self-Evolution . . . . . . . . . . . . . 14
6.2.1. Differential Semantic Pool and Trigger Mechanism . . 14
6.2.2. Schema Self-Evolution Algorithm . . . . . . . . . . . 15
6.2.3. Long-Term Evaluation Mechanism . . . . . . . . . . . 16
7. Security Considerations . . . . . . . . . . . . . . . . . . . 18
8. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 18
9. References . . . . . . . . . . . . . . . . . . . . . . . . . 18
9.1. Normative References . . . . . . . . . . . . . . . . . . 18
9.2. Informative References . . . . . . . . . . . . . . . . . 19
Appendix A. Example Messages . . . . . . . . . . . . . . . . . . 19
A.1. Schema Negotiation Request and Response . . . . . . . . . 19
A.2. Structured Payload Exchange . . . . . . . . . . . . . . . 20
A.3. Photo Editing Schema Example . . . . . . . . . . . . . . 20
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 21
Zhou & Peng Expires 24 December 2026 [Page 2]
Internet-Draft Structured Data Schema Interaction June 2026
1. Introduction
Recent advances in large language models (LLMs) enable AI agents to
plan and execute multi-step workflows for complex tasks. Through
agent communication protocols, AI agents can call third-party tools
and delegate tasks to other AI agents. When an AI agent acts on
behalf of a human user, these interoperations require structured,
deterministic, and efficient information exchange.
Today's agent ecosystems are characterized by rich, heterogeneous
interaction information. Agents communicate through natural language
text, structured data, and platform-specific documents. While
natural language is expressive and flexible, it introduces three
critical problems in multi-agent collaboration:
* Semantic drift: Without structured constraints, LLM-based parsing
of natural language produces inconsistent semantic interpretations
across heterogeneous agents with different LLMs, leading to
semantic drift and causing miscommunication.
* High inference overhead: Processing free-form text requires
substantial reasoning tokens and computational resources,
increasing end-to-end latency and operational costs.
* Interoperability barriers: Heterogeneous agents (e.g., payment
agents, lifestyle service agents) lack a unified model alignment
mechanism, making cross-system communication fragile and
integration-costly.
This document introduces a structured data schema protocol, providing
explicit semantic definitions with fixed data keys. The benefits of
this approach are:
1. Deterministic semantic alignment: By pre-defining key-value
schemas with explicit semantic descriptions, client agents can
parse user intent into structured payloads with minimal
ambiguity, effectively suppressing semantic drift.
2. Reduced token consumption and response latency: Structured
communication eliminates the need for server-side agents to
perform open-ended natural language understanding.
3. Enhanced interoperability and decoupling: A standardized key-
value format allows client agents to adapt dynamically to server
agent interface changes, enabling massive heterogeneous agent
onboarding without per-integration custom parsing logic.
Zhou & Peng Expires 24 December 2026 [Page 3]
Internet-Draft Structured Data Schema Interaction June 2026
This protocol is designed to complement existing agent protocols
(e.g., A2A [A2A], MCP [MCP]) by defining the data-mode contract. It
does not mandate transport and authorization mechanisms; those may be
provided by underlying protocols. Existing structured data exchange
protocols such as JMAP Sharing [RFC9670] demonstrate that
standardized key-value data models with explicit sharing semantics
can enable scalable cross-system interoperability, providing a design
precedent for agent-to-agent schema negotiation.
1.1. 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.
2. Terminology
AI Agent
An entity with built-in intelligence, which can perform actions to
accomplish tasks, possibly on behalf of an end-user or another
agent.
Client Agent
The agent that initiates a structured interaction request,
typically acting on behalf of an end-user.
Server Agent
The agent that exposes structured capabilities and responds to
client agent requests with key-value formatted data.
Data Schema (Schema)
An LLM-readable template that defines the set of keys, value
types, and semantic descriptions required for a specific
interaction scenario.
Semantic Annotation
A human/LLM-readable description associated with a schema key,
explaining its meaning, expected value range, and key semantics.
Structured Communication
The practice of exchanging information strictly within the
boundaries of an agreed-upon data schema, as opposed to free-form
natural language.
Zhou & Peng Expires 24 December 2026 [Page 4]
Internet-Draft Structured Data Schema Interaction June 2026
Schema Negotiation
The process by which a client agent discovers and obtains the data
schema and semantic annotations from a server agent prior to
sending structured payload.
Schema Update
An OPTIONAL mechanism by which a server agent refines its
published schema based on observed dynamic usage patterns,
returning updated new key definitions to the client agent.
3. Protocol Overview
The Structured Data Schema Interaction Protocol operates in three
phases: Schema Negotiation, Structured Data Schema Exchange, and
(optionally) Schema Update. The protocol assumes that transport-
level connectivity (e.g., HTTP, JSON-RPC, or protocol-specific
channels) has already been established by underlying agent
communication frameworks.
3.1. Interaction Model
The protocol adopts a client-server interaction model between two
cooperating agents:
Client Agent (C)
The agent that requires a service. It is responsible for (1)
discovering the server agent's schema, (2) mapping user intent or
upstream data into the negotiated key-value structure, and (3)
transmitting the structured payload.
Server Agent (S)
The agent that exposes a capability. It is responsible for (1)
publishing its key-value schema and semantic annotations, (2)
validating incoming structured payloads against the schema, (3)
executing the requested capability, and (4) optionally returning
schema refinement suggestions.
The interaction is stateless from the protocol perspective; any
session state MUST be managed by the application layer or underlying
transport protocol.
3.2. Message Flow
Figure 1 illustrates the complete message flow of a structured key-
value interaction.
Zhou & Peng Expires 24 December 2026 [Page 5]
Internet-Draft Structured Data Schema Interaction June 2026
+--------+ +--------+ +----------------+
|End User| | Client | | Server |
| | | Agent | | Agent |
+---+----+ +---+----+ +-------+--------+
| | | |
| (1) Natural | | |
| language | | |
| request | | |
| - - - - - - - >| | |
| | | |
| |----\ | |
| | | (2) Agent | |
| | | discovery | |
| | | + scenario| |
| | | id | |
| |<---/ | |
| | | |
| | (3) Get schema | |
| | for scenario | |
| |------------------->| |
| | | |
| | (3) Schema + | |
| | semantic desc. | |
| |< - - - - - - - - - | |
| | | |
| |----\ | |
| | | (4) LLM-based | |
| | | parsing | |
| | | + mapping | |
| |<---/ | |
| | | |
| | (5) Structured | |
| | payload | |
| |------------------->| |
| | | |
| | (6) Execution | |
| | result | |
| |< - - - - - - - - - | |
| | | |
| | (7) Optional | |
| | schema update | |
| |< - - - - - - - - - | |
| | | |
+---+----+ +---+----+ +-------+--------+
|End User| | Client | | Server |
| | | Agent | | Agent |
+--------+ +--------+ +----------------+
Zhou & Peng Expires 24 December 2026 [Page 6]
Internet-Draft Structured Data Schema Interaction June 2026
Figure 1: Structured Key-Value Schema Interaction Message Flow
Step (1) User Request: The end user provides a natural language
request to the client agent (e.g., "Help me order a large iced latte"
or "Retouch this photo with a vintage filter"). This request is
unconstrained free-form text that expresses the user's intent but
does not yet identify the target service or data structure.
Step (2) Agent Discovery and Scenario Identification: The client
agent analyzes the user's request using its internal LLM or intent-
classification component to determine:
* Target Server Agent: Which remote agent can fulfill the request
(e.g., an airline service agent).
* Interaction Scenario: The specific capability or workflow category
within the target agent (e.g., "flight_booking", "photo_retouch").
This step MAY leverage an agent registry, capability directory, or
historical context to disambiguate between multiple candidate server
agents. If no suitable server agent is found, the client agent
SHOULD report the failure to the end user.
Step (3) Schema Negotiation: The client agent requests the server
agent's schema template and semantic descriptions for a given
interaction scenario (e.g., flight booking, photo editing). The
server agent returns a JSON object containing the schema keys, value
types, and semantic annotations.
Step (4) Structured Exchange: The client agent transmits the
populated key-value payload to the server agent. All REQUIRED keys
MUST be present; OPTIONAL keys MAY be omitted if not applicable.
Step (5) Execution Result: The server agent validates the payload,
executes the requested capability, and returns a result. The result
itself SHOULD be structured according to a pre-negotiated response
schema when applicable.
Step (6) Optional Schema Update: If the server agent observes
recurring patterns in the "other" key or receives explicit capability
extension requests, it MAY return a schema update suggestion
containing new keys or refined semantic descriptions. This step is
OPTIONAL and serves as a lightweight feedback loop for long-term
protocol refinement.
Zhou & Peng Expires 24 December 2026 [Page 7]
Internet-Draft Structured Data Schema Interaction June 2026
4. Structured Key-Value Format
Structured data formats such as JSContact [RFC9610] demonstrate that
explicitly typed keys with semantic annotations enable reliable
machine parsing. This protocol applies the same principle to agent-
to-agent communication: every key in the schema template carries a
declared type and a semantic description that constrains the client
agent's generation space.
This section defines the syntax and semantics of the structured key-
value interaction format.
4.1. Schema Template
A schema template is a JSON object that declares the expected
structure of an interaction payload. It MUST contain the following
top-level members:
schema_id
REQUIRED. A string that uniquely identifies the schema version
within the server agent's namespace.
scenario
REQUIRED. A human-readable string describing the interaction
scenario (e.g., "flight booking", "photo_retouch").
keys
REQUIRED. An array of key definition objects, each describing a
single key expected in the payload.
Each key definition object MUST contain:
key_name
REQUIRED. A string identifier for the key, using snake_case
convention. Key names MUST be unique within the schema.
key_type
REQUIRED. A JSON Schema type identifier (e.g., "string",
"integer", "boolean", "array", "object").
Zhou & Peng Expires 24 December 2026 [Page 8]
Internet-Draft Structured Data Schema Interaction June 2026
semantic_description
REQUIRED. A human-readable and machine-processable string
explaining the business meaning of the key, acceptable value
enumerations, and mapping examples from natural language. This
description serves as a prompt-level anchor for the client agent's
LLM, constraining the generation space and reducing hallucinated
key mappings. Server agents SHOULD maintain semantic descriptions
in the same language as the expected end-user queries, or provide
multilingual annotations when serving cross-lingual client agents.
required
REQUIRED. A boolean indicating whether the key MUST be present in
the payload.
default_value
OPTIONAL. A default value to be used when the key is omitted and
not required. If absent and the key is optional, the server agent
MUST apply its own default logic or ignore the key.
Figure 2 shows an example schema template for a flight booking
purchase scenario.
{
"schema_id": "flight_booking_v1",
"scenario": "flight_booking",
"keys": [
{
"key_name": "origin",
"key_type": "string",
"required": true,
"default_value": null,
"semantic_description": "Departure city or airport code. Acceptable values: IATA airport codes (e.g., PEK, SHA, JFK) or city names in English or local language. Example mapping: 'from Beijing' -> 'PEK'."
},
{
"key_name": "destination",
"key_type": "string",
"required": true,
"default_value": null,
"semantic_description": "Arrival city or airport code. Acceptable values: IATA airport codes or city names. Example mapping: 'to Shanghai' -> 'SHA'."
},
{
"key_name": "departure_date",
"key_type": "string",
"required": true,
"default_value": null,
"semantic_description": "Date of departure in ISO 8601 format (YYYY-MM-DD). Example mapping: 'next Monday' -> '2026-05-04'."
},
{
Zhou & Peng Expires 24 December 2026 [Page 9]
Internet-Draft Structured Data Schema Interaction June 2026
"key_name": "cabin_class",
"key_type": "string",
"required": false,
"default_value": "economy",
"semantic_description": "Cabin class preference. Acceptable values: economy, premium_economy, business, first. Example mapping: 'business class' -> 'business'."
},
{
"key_name": "passenger_count",
"key_type": "integer",
"required": false,
"default_value": 1,
"semantic_description": "Number of passengers. Range: 1-9. Example mapping: 'two people' -> 2."
},
{
"key_name": "other",
"key_type": "string",
"required": false,
"default_value": null,
"semantic_description": "Escape valve for unstructured semantic fragments that cannot be mapped to existing keys. Example mapping: 'window seat please' -> 'window seat'."
}
]
}
Figure 2: Example Schema Template for Flight Booking
4.2. Semantic Annotation
Semantic annotations provide the contextual anchor that enables
client agent LLMs to perform accurate intent-to-key mapping. Each
key definition in the schema template MUST be augmented with a
"semantic_description" field, as required in Section 4.1.
The semantic description serves as a prompt-level anchor for the
client agent's LLM, constraining the generation space and reducing
hallucinated key mappings. Figure 3 extends the flight booking
example with a focused semantic annotation.
{
"key_name": "cabin_class",
"key_type": "string",
"required": false,
"default_value": "economy",
"semantic_description": "Cabin class preference. Acceptable values: economy, premium_economy, business, first. Example mapping: 'business class' -> 'business'."
}
Figure 3: Semantic Annotation Example
Zhou & Peng Expires 24 December 2026 [Page 10]
Internet-Draft Structured Data Schema Interaction June 2026
Server agents SHOULD maintain semantic descriptions in the same
language as the expected end-user queries, or provide multilingual
annotations when serving cross-lingual client agents.
4.3. The "other" Key
The key named "other" is reserved within every schema template as an
escape valve for unstructured semantic fragments that cannot be
mapped to existing keys. Its usage is subject to the following
rules:
* The "other" key MUST be defined as OPTIONAL (required: false).
* The value of the "other" key MUST be a string or an array of
strings containing natural language descriptions of unmapped user
intent.
* Server agents MUST accept payloads containing the "other" key
without rejecting the request, even if the key contains
information outside the current schema scope.
* Client agents SHOULD minimize the use of the "other" key by
leveraging LLM-based parsing to exhaust existing keys before
falling back to "other".
The presence of meaningful content in the "other" key signals a
potential schema coverage gap. Server agents MAY use this signal as
input to the OPTIONAL schema update mechanism described in
Section 6.2.
5. Illustrations of the protocol
This section illustrates the application of the structured key-value
interaction protocol.
5.1. Flight Booking
Scenario: An end user asks a personal AI assistant (client agent) to
book a flight through an airline service agent (server agent).
User utterance: "Book me a flight from Beijing to Shanghai next
Monday, business class, and I prefer a window seat."
Schema negotiation: The client agent requests the flight booking
schema from the server agent. The server agent returns the schema
template shown in Figure 2, augmented with semantic annotations.
Intent parsing and mapping:
Zhou & Peng Expires 24 December 2026 [Page 11]
Internet-Draft Structured Data Schema Interaction June 2026
* "Beijing" -> origin: "PEK"
* "Shanghai" -> destination: "SHA"
* "next Monday" -> departure_date: "2026-05-04"
* "business class" -> cabin_class: "business"
* (implicit) -> passenger_count: 1
* "window seat" -> other: "window seat"
Structured payload:
{
"schema_id": "flight_booking_v1",
"payload": {
"origin": "PEK",
"destination": "SHA",
"departure_date": "2026-05-04",
"cabin_class": "business",
"passenger_count": 1,
"other": "window seat"
}
}
Figure 4: Structured Payload for Flight Booking
Execution: The server agent validates the payload, queries the flight
inventory, and returns a booking confirmation with flight number,
departure time, and seat assignment.
Optional schema update: If the server agent observes frequent "other"
entries mentioning seat preferences, it MAY return a schema update
suggestion adding a "seat_preference" key with acceptable values
"window", "aisle", or "none".
5.2. Photo Editing
Scenario: An end user asks a personal AI assistant to retouch a photo
through a cloud-based image editing agent.
User utterance: "Please retouch this photo: smooth the skin, whiten
teeth, make the background blurry, and add a vintage filter. Also, I
want my eyes to look bigger."
Zhou & Peng Expires 24 December 2026 [Page 12]
Internet-Draft Structured Data Schema Interaction June 2026
Schema negotiation: The client agent discovers the photo editing
schema from the server agent. Example keys include: skin_smoothing
(integer 0-10), teeth_whitening (boolean), background_blur (boolean),
filter_style (string), eye_enlargement (boolean).
Intent parsing and mapping:
* "smooth the skin" -> skin_smoothing: 7
* "whiten teeth" -> teeth_whitening: true
* "make the background blurry" -> background_blur: true
* "add a vintage filter" -> filter_style: "vintage"
* "eyes to look bigger" -> other: "increase eye size proportionally"
Structured payload:
{
"schema_id": "photo_retouch_v2",
"payload": {
"skin_smoothing": 7,
"teeth_whitening": true,
"background_blur": true,
"filter_style": "vintage",
"eye_enlargement": false,
"other": "increase eye size proportionally"
}
}
Figure 5: Structured Payload for Photo Editing
Note: The client agent mapped "eyes to look bigger" to the "other"
key because the current schema does not define a granular eye_size
adjustment key (only a boolean eye_enlargement). The server agent
MAY later propose a schema update introducing "eye_size_scale"
(float, 1.0-1.5) based on aggregated "other" patterns.
6. Capability Enhancement
This section describes OPTIONAL mechanisms that enhance the core
structured interaction protocol. Implementations MAY support none,
some, or all of these capabilities. They are designed to be
transparent to agents that do not implement them.
Zhou & Peng Expires 24 December 2026 [Page 13]
Internet-Draft Structured Data Schema Interaction June 2026
6.1. LLM-based Semantic Parsing
The protocol assumes that client agents employ an internal LLM to
perform natural language understanding (NLU) and map user intent to
schema keys. The quality of this mapping directly affects the
correctness of the structured payload.
Recommended practices for LLM-based semantic parsing include:
* In-context learning: Provide the LLM with the schema template and
semantic descriptions as part of the prompt context, enabling few-
shot or zero-shot key extraction.
* Constrained decoding: Where supported, use constrained generation
or grammar-based decoding to ensure that the LLM output conforms
to the expected key-value JSON structure.
* Confidence thresholding: If the LLM's confidence in mapping a
semantic fragment to a specific key falls below a configurable
threshold, the fragment SHOULD be routed to the "other" key rather
than risk a hallucinated mapping.
Server agents are NOT REQUIRED to perform NLU; their role is to
validate and execute structured payloads. This separation of
concerns reduces server-side inference costs and ensures
deterministic execution.
6.2. Key-Value Schema Self-Evolution
The schema self-evolution mechanism provides a dynamic, backward-
compatible path for server agents to refine their published schemas
based on operational feedback and differential semantics extracted
from the "other" key. It is OPTIONAL and does not alter the core
structured exchange semantics.
The mechanism consists of three coordinated components: (1) a trigger
mechanism based on a differential semantic pool, (2) a schema self-
evolution algorithm that generates dynamic patches, and (3) a long-
term evaluation framework that ensures convergence and prevents
schema bloat.
6.2.1. Differential Semantic Pool and Trigger Mechanism
To avoid erroneous evolution caused by sporadic anomalies and to
ensure that genuine common or personalized needs are not missed,
server agents MAY maintain a Differential Semantic Pool (DSP).
Zhou & Peng Expires 24 December 2026 [Page 14]
Internet-Draft Structured Data Schema Interaction June 2026
The DSP collects natural-language fragments from the "other" key that
could not be mapped to existing schema keys. Its operation follows
three stages:
Semantic Vector Clustering
Each fragment extracted from the "other" key MUST be encoded into
a semantic vector. Server agents SHOULD use dense vector
embeddings (e.g., sentence-transformer-based) to represent
semantic meaning. Vectors are clustered using similarity
thresholds (e.g., cosine similarity >= 0.85). Each cluster
represents a distinct, recurring semantic intent that is not
covered by the current schema.
Heat Decay Counting
Each cluster maintains a heat score that reflects the intensity of
the corresponding semantic demand. When a new fragment joins a
cluster, its heat score increases by a fixed increment. The heat
score MUST decay over time (e.g., exponential decay with a half-
life of 24 hours) to prevent obsolete or transient patterns from
accumulating undue weight.
Threshold-Based Triggering
A schema evolution trigger fires when a cluster's heat score
exceeds a configurable evolution threshold (e.g., 50 accumulated
heat units) AND the cluster contains a minimum number of distinct
source requests (e.g., >= 5 unique client agents or >= 10 total
occurrences within a 7-day window). This dual-gate design ensures
that evolution is triggered only when the same semantic appeal has
gathered sufficient strength across multiple interactions,
filtering out accidental outliers while capturing genuine
collective needs.
Server agents MAY maintain separate DSP instances per scenario or per
client-agent cohort, enabling both global schema evolution and
personalized schema branching.
6.2.2. Schema Self-Evolution Algorithm
Once the trigger mechanism identifies a mature semantic cluster, the
server agent executes a self-evolution algorithm to synthesize a
schema patch from the cluster's natural-language content.
Base Schema
The immutable, versioned schema template (see Section 4.1) that
defines the stable contract. Base schema keys MUST NOT be removed
or have their types changed by dynamic patches; only additive or
semantic-description refinements are permitted in the patch layer.
Zhou & Peng Expires 24 December 2026 [Page 15]
Internet-Draft Structured Data Schema Interaction June 2026
Dynamic Patch Generation
For each triggered semantic cluster, the server agent MUST perform
intent induction, conflict detection, and patch packaging.
Online Update Delivery
The server agent MAY deliver active patches through inline
suggestions in the schema_update_suggestion field of the execution
result response or through a dedicated schema polling endpoint.
Personalized Adaptation
Server agents MAY maintain per-client patch stacks. When a
specific client agent repeatedly submits personalized requests
that fall into a unique semantic cluster (e.g., a frequent
business traveller who always requests "extra legroom" and "quiet
cabin"), the server agent MAY generate a client-specific patch
that adds keys such as "seat_preference" and "cabin_zone" only for
that client. This transforms standardized task flows into
privately customized service responses without polluting the
global schema.
* Intent Induction: Use an internal LLM or rule-based extractor to
summarize the cluster's natural-language fragments into a
candidate key_name, key_type, required flag, default_value, and
semantic_description. The semantic_description MUST include
mapping examples derived from real fragments in the cluster.
* Conflict Detection: Before finalizing the patch, the server agent
MUST check that the candidate key_name does not collide with
existing keys in the base schema or active patches. If a
collision occurs, the server agent SHOULD merge the candidate into
the existing key by refining its semantic_description rather than
creating a duplicate.
* Patch Packaging: The approved candidate is packaged as a schema
patch containing new_keys, modified_keys, or both. The patch MUST
carry a patch_id, a parent_schema_id, a timestamp, and an
expiration date.
6.2.3. Long-Term Evaluation Mechanism
To prevent schema bloat and the accumulation of erroneous keys,
server agents that implement self-evolution MUST employ a long-term
evaluation mechanism that continuously assesses the quality and
necessity of every patch key.
Evaluation Metrics: For each key introduced through a dynamic patch,
the server agent SHOULD track at minimum the following metrics over a
configurable observation window (default 30 days):
Zhou & Peng Expires 24 December 2026 [Page 16]
Internet-Draft Structured Data Schema Interaction June 2026
* usage_frequency: The ratio of payloads in which the key is present
to total payloads for the scenario.
* semantic_alignment_accuracy: The ratio of payloads where the key's
value matches the intent expressed in the original natural-
language request, as judged by an internal LLM or manual audit
sampler.
* value_type_correctness: The ratio of payloads where the received
value conforms to the declared key_type.
* client_adoption_rate: The ratio of distinct client agents that
have successfully adopted the key to those that received the
patch.
Two-Phase Lifecycle: All new keys introduced via dynamic patches MUST
begin in an experimental state and transition through two phases.
Trial Period and Stabilization Decision
The key remains experimental for a configurable duration (default
7 days). During this period, the server agent collects the
metrics above. The key MUST be advertised with an "experimental:
true" flag in the patch so that client agents know the key is
provisional. Upon completion of the trial period, the server
agent evaluates the aggregated metrics.
Schema Convergence Guard
The server agent MUST enforce a maximum limit on the number of
active experimental keys per scenario (e.g., no more than 10).
When the limit is reached, new triggers MUST be queued until
existing experimental keys are either promoted or deprecated.
This guard prevents runaway schema bloat and ensures that the
protocol converges to a stable, high-signal key set over time.
* Promotion: If usage_frequency >= 15%, semantic_alignment_accuracy
>= 80%, and value_type_correctness >= 90%, the key is promoted to
stable. The "experimental" flag is removed, and the key becomes
part of the long-term supported schema.
* Deprecation: If usage_frequency < 5% OR
semantic_alignment_accuracy < 60% OR value_type_correctness < 70%,
the key is marked deprecated. Deprecated keys remain in the
schema for a grace period (default 14 days) with a "deprecated:
true" flag, after which they MAY be moved to a withdrawn state.
Zhou & Peng Expires 24 December 2026 [Page 17]
Internet-Draft Structured Data Schema Interaction June 2026
* Withdrawal: A withdrawn key is removed from active patches.
Server agents MUST still accept the key in incoming payloads for
an additional backward-compatibility window (default 30 days) to
avoid breaking legacy client agents, but SHOULD log a warning.
7. Security Considerations
Structured key-value payloads may contain sensitive personal
information (e.g., dietary preferences, biometric retouching
parameters, location data). Implementations MUST protect this data
in transit and at rest using mechanisms appropriate to their threat
model.
Schema negotiation and update messages MUST be integrity-protected to
prevent man-in-the-middle attacks that could inject malicious keys or
semantic descriptions designed to exfiltrate data or trigger
unauthorized actions.
When the "other" key contains free-form natural language, server
agents MUST apply the same input validation and sanitization
practices as they would for any natural language input, preventing
prompt injection or command injection attacks.
The OPTIONAL schema update mechanism MUST require authentication and
authorization if it exposes new capabilities or modifies security-
relevant keys (e.g., keys related to payment, identity, or access
control).
8. IANA Considerations
This document has no IANA actions.
9. References
9.1. Normative References
[RFC9670] Jenkins, N., Ed., "JSON Meta Application Protocol (JMAP)
Sharing", RFC 9670, DOI 10.17487/RFC9670, November 2024,
<https://www.rfc-editor.org/info/rfc9670>.
[RFC9610] Jenkins, N., Ed., "JSON Meta Application Protocol (JMAP)
for Contacts", RFC 9610, DOI 10.17487/RFC9610, December
2024, <https://www.rfc-editor.org/info/rfc9610>.
[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/info/rfc2119>.
Zhou & Peng Expires 24 December 2026 [Page 18]
Internet-Draft Structured Data Schema Interaction June 2026
[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/info/rfc8174>.
9.2. Informative References
[A2A] Google, "Agent2Agent(A2A) Protocol", 2025,
<https://a2a-protocol.org/latest>.
[MCP] Anthropic, "Model Context Protocol (MCP)", 2025,
<https://modelcontextprotocol.io/docs/getting-started/
intro>.
Appendix A. Example Messages
This appendix provides complete, non-normative examples of schema
negotiation, structured payload exchange, and optional schema update
messages.
A.1. Schema Negotiation Request and Response
Client agent request:
{
"method": "get_schema_template",
"params": {
"scenario": "flight_booking",
"preferred_language": "en-US"
}
}
Figure 6: Schema Negotiation Request
Server agent response:
{
"schema_id": "flight_booking_v1",
"scenario": "flight_booking",
"keys": [
{"key_name": "origin", "key_type": "string", "required": true, "semantic_description": "Departure city or airport code. Acceptable values: IATA airport codes (e.g., PEK, SHA, JFK) or city names. Example: 'from Beijing' -> 'PEK'."},
{"key_name": "destination", "key_type": "string", "required": true, "semantic_description": "Arrival city or airport code. Example: 'to Shanghai' -> 'SHA'."},
{"key_name": "departure_date", "key_type": "string", "required": true, "semantic_description": "Departure date in ISO 8601 format (YYYY-MM-DD). Example: 'next Monday' -> '2026-05-04'."},
{"key_name": "cabin_class", "key_type": "string", "required": false, "default_value": "economy", "semantic_description": "Cabin class. Acceptable values: economy, premium_economy, business, first. Example: 'business class' -> 'business'."},
{"key_name": "passenger_count", "key_type": "integer", "required": false, "default_value": 1, "semantic_description": "Number of passengers. Range: 1-9. Example: 'two people' -> 2."},
{"key_name": "other", "key_type": "string", "required": false, "semantic_description": "Natural-language descriptions that cannot be mapped to existing keys. Example: 'window seat' -> 'window seat'."}
]
}
Zhou & Peng Expires 24 December 2026 [Page 19]
Internet-Draft Structured Data Schema Interaction June 2026
Figure 7: Schema Negotiation Response
A.2. Structured Payload Exchange
Client agent request payload:
{
"schema_id": "flight_booking_v1",
"payload": {
"origin": "PEK",
"destination": "SHA",
"departure_date": "2026-05-04",
"cabin_class": "business",
"passenger_count": 1,
"other": "window seat"
}
}
Figure 8: Client Agent Request Payload
Server agent response:
{
"booking_id": "BK-20260430-001",
"status": "confirmed",
"flight_number": "CA1234",
"departure_time": "2026-05-04T09:00:00+08:00",
"arrival_time": "2026-05-04T11:20:00+08:00",
"seat": "12A",
"total_amount": "CNY 2,450.00",
"schema_update_suggestion": {
"new_keys": [
{
"key_name": "seat_preference",
"key_type": "string",
"required": false,
"default_value": "none",
"semantic_description": "Seat preference. Acceptable values: window, aisle, none."
}
]
}
}
Figure 9: Server Agent Response
A.3. Photo Editing Schema Example
Zhou & Peng Expires 24 December 2026 [Page 20]
Internet-Draft Structured Data Schema Interaction June 2026
{
"schema_id": "photo_retouch_v2",
"scenario": "photo_retouch",
"keys": [
{"key_name": "skin_smoothing", "key_type": "integer", "required": false, "default_value": 0, "semantic_description": "Skin smoothing intensity. Range: 0-10, where 0 means off. Example: 'light skin smoothing' -> 3."},
{"key_name": "teeth_whitening", "key_type": "boolean", "required": false, "default_value": false, "semantic_description": "Whether teeth whitening is enabled. Example: 'make the teeth whiter' -> true."},
{"key_name": "background_blur", "key_type": "boolean", "required": false, "default_value": false, "semantic_description": "Whether background blur is enabled. Example: 'blur the background' -> true."},
{"key_name": "filter_style", "key_type": "string", "required": false, "default_value": "none", "semantic_description": "Filter style. Acceptable values: none, vintage, cinematic, warm, cool. Example: 'vintage style' -> 'vintage'."},
{"key_name": "eye_enlargement", "key_type": "boolean", "required": false, "default_value": false, "semantic_description": "Whether eye enlargement is enabled. Note: this key is a boolean switch; use other for fine-grained adjustment requests."},
{"key_name": "other", "key_type": "string", "required": false, "semantic_description": "Photo-editing requirements that cannot be mapped to existing keys. Example: 'make the eyes a little bigger' -> 'increase eye size proportionally'."}
]
}
Figure 10: Photo Editing Schema Example
Authors' Addresses
Fangtong Zhou
Huawei Technologies
Huawei Bld., No.156 Beiqing Rd.
Beijing
100095
China
Email: zhoufangtong@huawei.com
Shuping Peng
Huawei Technologies
Huawei Bld., No.156 Beiqing Rd.
Beijing
100095
China
Email: pengshuping@huawei.com
Zhou & Peng Expires 24 December 2026 [Page 21]