Progressive disclosure improves agent skills quality but adds delay
Report: Progressive Disclosure of Agent Skills
Artificial Intelligence
Summary
Large language model agents can do more things when given extra skills, but having too many skills makes them expensive to run. The authors studied turning on skills only when needed, called progressive disclosure, to save costs. They found this approach makes it easier for the agent to pick the right skill but slightly slows down how fast it answers. So, adding skills gradually helps quality but at a small speed cost.
What this means in practice
- •For enterprise software developers: Optimize AI agent costs by activating features only when needed, improving skill selection quality.
- •For customer support platform engineers: Improve response accuracy in AI agents by loading relevant skills progressively, balancing speed and precision.
Authors
Guilin Zhang, Kai Zhao, Priyanka Mudgal, Waleed Ammar, Xiquan Cui, Xu Chu, Alet Blanken
Abstract
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.