Introduces Diverse Skill Routing (DSR), a reranking framework for LLM agents that uses a Determinantal Point Process with a query-residual diversity kernel to balance relevance against redundancy when selecting skills from large registries. Addresses the failure mode where independent relevance ranking wastes context budget on functionally redundant skills for multi-skill tasks. On the SkillRouter benchmark, DSR improves recall and full coverage over a strong pointwise reranking baseline, with the largest gains on multi-skill queries.
