SkillSelect-Serve: Budget-Controllable and QoS-Aware Skill Service Recommendation and Composition for Small LLM Agents
This work addresses the need for cost-effective and quality-aware skill selection in LLM agent systems, offering a practical solution for resource-constrained deployments.
SkillSelect-Serve introduces a budget-controllable and QoS-aware framework for selecting and composing skill services for LLM agents, outperforming fixed top-k retrieval baselines in bundle recall and mean utility across 35,353 skills and 586 task queries.
Reusable skill libraries are becoming important infrastructure for large language model (LLM) agents, yet existing selection methods often treat skills as retrievable documents and return fixed top-k lists. This paper presents SkillSelect-Serve, a budget-controllable and QoS-aware framework that formulates agent skill selection as Skill Service Recommendation and Composition. SkillSelect-Serve represents raw skills as structured Skill Services with functional descriptions, dependencies, context cost, risk, and QoS-related attributes. A local Micro-Agent Requirement Planner converts natural-language tasks into structured service requirements, while a shared discovery backbone retrieves candidate services from a large registry. The framework then performs dual-granularity utility modeling with skill-level marginal suitability estimation and bundle-level calibration for coverage, redundancy, cost, and risk trade-offs. Experiments on 35,353 skills and 586 task queries show that SkillSelect-Serve consistently improves same-budget bundle recall and mean utility over fixed top-k retrieval baselines.