超越Top-$k$技能检索：面向LLM智能体的多样性感知技能路由

中文摘要 AI 辅助

大型语言模型（LLM）智能体日益依赖外部技能，但在大型技能库上路由用户请求是困难的，因为许多技能在功能上是冗余的，而复杂任务往往需要互补的技能组合。现有的技能路由器通常独立地按查询相关性对候选技能进行排序，这可能会在冗余技能上浪费上下文预算。我们提出了多样性感知技能路由（DSR），一种基于行列式点过程的多样性感知重排序框架，用于平衡相关性和非冗余性。DSR引入了一个查询残差多样性核，该核惩罚冗余的技能重叠，同时减少仅由共享查询相关性引起的惩罚。在SkillRouter基准上，与强点式重排序基线相比，DSR提高了召回率和完全覆盖率，在多技能查询上取得了更大的提升。这些结果表明，技能路由不仅应被视为相关性排序，还应被视为互补集合选择。

英文摘要

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.

发表机构

• Virginia Tech（弗吉尼亚理工大学）
• University of Southern California（南加州大学）
• Adobe Research（Adobe研究院）
• Dolby Labs（杜比实验室）
• Texas A&M University（德克萨斯A&M大学）
• Arizona State University（亚利桑那州立大学）

机构由 AI 辅助整理，请以论文原文为准。