{"ID":2922152,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-02T17:44:34.312992241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.00822","arxiv_id":"2606.00822","title":"SkillPager: Query-Adaptive Intra-Skill Navigation via Semantic Node Retrieval","abstract":"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.","short_abstract":"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. W...","url_abs":"https://arxiv.org/abs/2606.00822","url_pdf":"https://arxiv.org/pdf/2606.00822v1","authors":"[\"Zicai Cui\",\"Zihan Guo\",\"Weiwen Liu\",\"Weinan Zhang\"]","published":"2026-05-30T17:49:07Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}