Metadata and Query Profile for Efficient Agent Discovery (draft-xu-efficient-agent-discovery-profile-01)
J. Xu, B. Li, R. Zhu (CAICT)
Standard body: IETF → (unit not yet charted)
Abstract
This document defines a metadata and query profile for efficient discovery of autonomous software agents. The profile describes how agents publish capability metadata using explicit tags, natural- language descriptions, example tasks, protocol bindings, and operational constraints. It also defines JSON metadata, discovery request, and discovery response objects that enable discovery services to combine structured filtering, semantic retrieval, and fine-grained matching while preserving an interoperable protocol surface. The profile does not mandate a specific machine-learning model, embedding model, database, or ranking algorithm. Instead, it standardizes the metadata and result evidence needed by clients and discovery services so that different implementations can interoperate while optimizing their own latency, scalability, and ranking quality.
Cite this entry
GB/T 7714-2015
J. Xu, B. Li, R. Zhu (CAICT). Metadata and Query Profile for Efficient Agent Discovery (draft-xu-efficient-agent-discovery-profile-01)[S/OL]. IETF Internet-Draft, Independent Submission(署名单位 CAICT,agentproto 方向),rev -01 提交于 2026-11-15(-00 为 2026-05-18);Abstract 取自 ietf.org/archive/id 官方 txt, 2026(2026-11-15)[2026-11-20]. https://datatracker.ietf.org/doc/draft-xu-efficient-agent-discovery-profile/.
BibTeX
@techreport{xu2026,
author = {J. Xu and B. Li and R. Zhu (CAICT)},
title = {Metadata and Query Profile for Efficient Agent Discovery (draft-xu-efficient-agent-discovery-profile-01)},
year = {2026},
organization = {IETF Internet-Draft, Independent Submission(署名单位 CAICT,agentproto 方向),rev -01 提交于 2026-11-15(-00 为 2026-05-18);Abstract 取自 ietf.org/archive/id 官方 txt},
howpublished = {\url{https://datatracker.ietf.org/doc/draft-xu-efficient-agent-discovery-profile/}},
} This entry is part of the AgentNet Observer library. Attribute with a link to this page when quoting.