Diverse Skill Routing is proposed, a diversity-aware reranking framework that uses a Determinantal Point Process to balance relevance and non-redundancy and improves recall and full coverage over a strong pointwise reranking baseline, with larger gains on multi-skill queries.
Abstract
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.
This work proposes SkillFeed, a progressive retrieve-and-rerank framework that first establishes task--skill alignment and then learns profile-conditioned discrimination, and introduces a profile-counterfactual benchmark, in which the task is held fixed while changes in the user profile induce changes in the reference...
Tian-Le Wang, Yang-He Zou, Xiang Liu et al.· 2 citations
Skill Retrieval (SR) aims to identify the most relevant skills from external skill libraries, and becomes increasingly challenging as libraries grow in scale and diversity. Existing methods either rank skills independently or rely on predefined graph propagation and hierarchical routing, making them vulnerable to seman...
Rong-Chen Zhao, Yu Chen, Yan-Min Yang et al.· 0 citations
Retrieval diversification is widely available in retrieval-augmented generation (RAG) frameworks, yet prior studies disagree on whether it improves retrieval and answer quality. We show that its effectiveness varies primarily with candidate-pool redundancy, in a pattern consistent with the number of distinct evidence p...
Guillaume Brouillette, Faustin Kagabo, Usef Faghihi et al.· 0 citations
Similar agent skills can share instructions but differ in their conditions of use. Query-based text selection may retain shared instructions and omit these distinctions. We introduce SkillContrast, a training-free selector that compares retrieved skills and retains their differing text with local context for a pretrain...
Jian-Dong Ding, Hong-Lei Ji, Ming Liu et al.· 0 citations
Skill2Query is a framework that first parses a skill document into a Skill Knowledge Graph and then generates pseudo-queries through a three-stage process including style mimicking, query template generation, and parameter filling, which consistently improves sparse, dense, and skill-routing retrieval.
Lihui Ding, Zi-Han Guo, Bingwei Lu et al.· 2 citations
Retrieval-Augmented Generation (RAG) systems typically apply identical retrieval logic to all user queries, overlooking that different query intents depend on fundamentally different document relationships. We propose QMEG, a query-aware retrieval framework that constructs a multi-relational evidence graph with five ac...
Jia-Run Pan, Yu-Ling Fan, Li Ma et al.· 2026 3rd International Confe...· 0 citations
