Semantic Routing for AI Agent Communication (draft-cui-semantic-routing-ai-agent-communication-00)
Yong Cui, Yihan Chao, Chenguang Du
Standard body: IETF → (unit not yet charted)
Abstract
AI agents often know the intended outcome of a task without knowing which agent, model, tool, workflow, or service should process it. This document describes an application-layer semantic routing framework that selects one Processing Target from task intent, execution context, target capabilities, constraints, and local policy. It defines a common operation-level information model and externally observable selection behavior that protocol bindings can preserve. Semantic matching is implementation-specific. This document does not define task decomposition, multi-agent orchestration, network-layer routing, target discovery, target invocation, or a new agent communication protocol.
Cite this entry
GB/T 7714-2015
Yong Cui, Yihan Chao, Chenguang Du. Semantic Routing for AI Agent Communication (draft-cui-semantic-routing-ai-agent-communication-00)[S/OL]. IETF Internet-Draft, Intended status: Informational (individual submission, DAWN, rev -00), 2026(2026-10-26)[2026-11-02]. https://datatracker.ietf.org/doc/draft-cui-semantic-routing-ai-agent-communication/.
BibTeX
@techreport{cui2026,
author = {Yong Cui and Yihan Chao and Chenguang Du},
title = {Semantic Routing for AI Agent Communication (draft-cui-semantic-routing-ai-agent-communication-00)},
year = {2026},
organization = {IETF Internet-Draft, Intended status: Informational (individual submission, DAWN, rev -00)},
howpublished = {\url{https://datatracker.ietf.org/doc/draft-cui-semantic-routing-ai-agent-communication/}},
} This entry is part of the AgentNet Observer library. Attribute with a link to this page when quoting.