研究库 论文知识库

内容库 / 论文

arXiv:2609.05824 · Agent 智能体

Beyond Top-k Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents

Beyond Top-k Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents

类型：arxiv
标识：2609.05824
链接：https://arxiv.org/abs/2609.05824
主分类：agent
形态：method
TLDR：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 penali
副分类：rag
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-14-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

笔记 LLM-Wiki / RAGSearch / GradRAG · 新型 RAG 范式综合 · 2026-07-28

仓库 AIDASLab/Awesome-LLM-Values-and-Pluralistic-Alignment

仓库 Dusto-AI/llm-situational-awareness-paper-list

笔记精读与批判 · From 128K to 4M: Efficient Training of Ultra-Long Context LLMs

笔记 Sebastian Raschka (Ahead of AI) · RSS 摘要

笔记知识库草稿 · Jay · 2026-07-01 午间补遗

arXiv

2609.05824

TLDR

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 penali

arXiv ↗ 中文全文