SkillPager: Query-Adaptive Intra-Skill Navigation via Semantic Node Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cui, Zicai, Guo, Zihan, Liu, Weiwen, Zhang, Weinan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918533736169472
author Cui, Zicai
Guo, Zihan
Liu, Weiwen
Zhang, Weinan
author_facet Cui, Zicai
Guo, Zihan
Liu, Weiwen
Zhang, Weinan
contents Skill-based LLM agents increasingly rely on long procedural documents, but full-document prompting wastes tokens and dilutes information critical to execution. We study this setting as intra-skill retrieval, where the goal is to select a minimal, execution-sufficient context from a known skill document given a query. We present SkillPager, a two-stage framework that parses each Markdown skill into typed semantic nodes offline and leverages Maximal Marginal Relevance (MMR) to perform global, query-conditioned node selection online. On a benchmark of 395 skills and 1,975 queries, SkillPager achieves 78.89% LLM-judged context sufficiency, compared to 82.23% for the exhaustive full-document baseline, while reducing prompt tokens by 47.04%. A granularity ablation shows that applying the same retrieval algorithm to raw fixed-length chunks reaches a comparable 81.77% sufficiency but increases token cost by 28.81%, demonstrating that efficiency gains are driven by typed semantic granularity rather than the retrieval algorithm alone. Among graph-based baselines, SkillPager outperforms the strongest baseline by a margin of 12.16%. Further ablations show that supporting content is most effective when retained in the candidate pool and selected adaptively rather than removed by static heuristics. These results identify typed intra-document retrieval as a distinct access problem for skill-based agents.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00822
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SkillPager: Query-Adaptive Intra-Skill Navigation via Semantic Node Retrieval
Cui, Zicai
Guo, Zihan
Liu, Weiwen
Zhang, Weinan
Information Retrieval
Artificial Intelligence
Skill-based LLM agents increasingly rely on long procedural documents, but full-document prompting wastes tokens and dilutes information critical to execution. We study this setting as intra-skill retrieval, where the goal is to select a minimal, execution-sufficient context from a known skill document given a query. We present SkillPager, a two-stage framework that parses each Markdown skill into typed semantic nodes offline and leverages Maximal Marginal Relevance (MMR) to perform global, query-conditioned node selection online. On a benchmark of 395 skills and 1,975 queries, SkillPager achieves 78.89% LLM-judged context sufficiency, compared to 82.23% for the exhaustive full-document baseline, while reducing prompt tokens by 47.04%. A granularity ablation shows that applying the same retrieval algorithm to raw fixed-length chunks reaches a comparable 81.77% sufficiency but increases token cost by 28.81%, demonstrating that efficiency gains are driven by typed semantic granularity rather than the retrieval algorithm alone. Among graph-based baselines, SkillPager outperforms the strongest baseline by a margin of 12.16%. Further ablations show that supporting content is most effective when retained in the candidate pool and selected adaptively rather than removed by static heuristics. These results identify typed intra-document retrieval as a distinct access problem for skill-based agents.
title SkillPager: Query-Adaptive Intra-Skill Navigation via Semantic Node Retrieval
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2606.00822