让大模型智能选技能，避免重复选择，提升复杂任务完成率
Beyond Top-$k$ Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents
- 用确定性点过程建模技能多样性，平衡相关性和去重
- 在多技能请求上召回率提升，全覆盖度显著优于传统方法
- 适合需要组合多个技能的复杂任务场景
大型语言模型（LLM）代理越来越依赖外部技能，但如何从大量技能库中路由用户请求仍具挑战：许多技能功能重叠，而复杂任务又需互补技能集。现有技能路由方法通常独立评估候选技能的相关性，易因冗余技能浪费上下文预算。本文提出多样性强的技能路由（DSR），采用确定性点过程（Determinantal Point Process）实现相关性与非冗余性的平衡。DSR引入查询残差多样性核函数，惩罚技能间重叠，同时降低仅由共享查询相关性带来的惩罚。在SkillRouter基准测试中，DSR相较强基线在召回率和全覆盖度上均有提升，尤其在多技能查询上增益更大。结果表明，技能路由不仅是相关性排序，更应视为互补技能集合的选择。
原文摘要 · Abstract (English)
Large language model (LLM) agents increasingly rely on external skills, but routing user requests over large skill registries is difficult because many skills are functionally redundant while complex tasks often require complementary skill sets. Existing skill routers typically rank candidates independently by query relevance, which can waste context budget on redundant skills. We propose Diverse Skill Routing (DSR), a diversity-aware reranking framework that uses a Determinantal Point Process to balance relevance and non-redundancy. DSR introduces a query-residual diversity kernel that penalizes redundant skill overlap while reducing penalties caused only by shared query relevance. On the SkillRouter benchmark, DSR improves recall and full coverage over a strong pointwise reranking baseline, with larger gains on multi-skill queries. These results suggest that skill routing should be treated not only as relevance ranking, but also as complementary set selection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。