发表机构
Workday; Workday AI Research（Workday公司; Workday AI研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本报告实证研究了智能体技能渐进式披露（懒加载）的效果，发现其能提升技能检索质量，但会略微增加整体延迟。
AI 中文摘要
Workday 部署的基于 LLM 的智能体的用户经常请求一些功能，这些功能可以通过在 LLM 上下文中定义命名过程（也称为技能）来解决，从而有效增强智能体的能力。然而，随着智能体技能库规模的增大，智能体的运营成本也随之增加。按需渐进式披露（懒加载）技能可能会降低运营成本，但其对整体延迟和技能检索质量的影响仍不清楚。在本报告中，我们通过实证研究探讨了这种影响，发现渐进式披露提高了技能检索质量，但略微降低了整体延迟。
英文摘要
Users of Workday's deployed LLM-based agents often request features which can be addressed by defining named procedures, also known as skills, in the LLM context, effectively augmenting agents' capabilities. However, as an agent's skills library grows in size, so does the agent's operational cost. Progressive disclosure (lazy-loading) of skills as needed may reduce operational costs, but its impact on overall latency and skill-retrieval quality remains unclear. In this report, we investigate the impact empirically and find that progressive disclosure improves skill-retrieval quality but marginally degrades overall latency.
