让现成检索模型学会匹配用户需求与可执行的智能体能力。
Adapting Embedding Models for Agent Capability Retrieval
- 用公开元数据构建能力描述，微调通用检索模型。
- 在两个未见目录上测试，性能均显著提升。
- 适合开发智能体市场或工具链的开发者参考。
开放智能体市场将原生智能体、工具包和可复用技能包在同一搜索界面中展示，但从业者仍缺乏跨混合目录检索的有效指导。本文研究现成检索模型（用于通用文本检索）是否可适应于匹配用户查询与可执行的智能体能力，以及学习到的信号能否在训练基准之外迁移。我们在AgentSelect数据集上对三种开源检索骨干模型（BGE-base、KaLM-v1.5、EasyRec）进行微调，该数据集将市场可见单元表示为从公开元数据生成的能力描述。测试在两个训练中未见的目录上进行：MuleRun原生智能体和包含50项技能、1,000个查询的ClawHub基准。结果表明，微调后模型在两个目录上均表现提升。代码与数据将在发表后公开。
原文摘要 · Abstract (English)
Open agent marketplaces list native agents, tool bundles, and reusable skill packages in the same search interface, yet practitioners still have little guidance on how to retrieve across this mixed catalog. We study whether off-the-shelf retrieval models, trained for general text retrieval, can be adapted to match user queries to executable agent capabilities, and whether the learned signal transfers beyond the benchmark used for tuning. We fine-tune three open retrieval backbones, BGE-base, KaLM-v1.5, and EasyRec, on AgentSelect, which represents marketplace-visible units as capability profiles derived from public metadata, and test transfer on two catalogs not seen during training: MuleRun native agents and a ClawHub benchmark of 50 skills with 1,000 queries. Adaptation helps on both catalogs. Code and data will be released upon publication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。