SkillSelect-Serve: Budget-Controllable and QoS-Aware Skill Service Recommendation and Composition for Small LLM Agents
arXiv:2607.00011v1 Announce Type: cross Abstract: 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 Mi
The proliferation of LLM agents drives an urgent need for efficient, context-aware skill management to move beyond basic retrieval methods.
This development addresses a critical bottleneck in deploying autonomous agents by enabling more sophisticated, resource-aware, and performant skill orchestration.
Agentic systems can now dynamically select and compose skills based on budget, quality of service, and dependencies, rather than static lists, enhancing their practical utility.
- · AI Agent developers
- · Enterprises deploying LLM agents
- · Cloud service providers (optimised agent compute)
- · Basic 'top-k' retrieval methods for agent skills
- · Inefficient monolithic AI models
Improved performance and cost-efficiency of LLM-powered autonomous agents.
Acceleration in the adoption and deployment of AI agents across various industries.
Increased demand for robust, granular 'skill service' marketplaces and infrastructure.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI