{"ID":6138332,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-11T15:39:16.154462532Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.07548","arxiv_id":"2607.07548","title":"Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?","abstract":"Large language model based search agents increasingly adopt multi-agent architectures in which a main agent decomposes a complex question into sub-queries and dispatches them to parallel sub-agents. However, existing systems instantiate all roles from a single model of identical scale, leaving open how model capacity should be distributed across roles. We factorize hierarchical search into three roles: a delegation role responsible for task decomposition, an execution role responsible for retrieval and evidence extraction, and an answer generation role held fixed as a confound control. We then conduct controlled capacity sweeps along the delegation and execution axes on five multi-hop QA benchmarks. The experiments yield three findings. First, role factorization consistently outperforms a single-agent baseline, improving exact match from 4.5 to 8.6 points across six model scales. Second, capacity sensitivity is asymmetric: scaling the delegation backbone improves EM by ~11 points, whereas scaling the execution sub-agent moves EM by only ~2.6 points, identifying decomposition as the capability bottleneck. Third, a 1.7B-parameter executor trained via quality-filtered trajectory distillation matches a frontier sub-agent in accuracy while consuming 37% fewer sub-agent tokens, advancing the Pareto frontier. These results suggest a concrete recipe for building hierarchical search agents: concentrate capacity at delegation and downsize execution without sacrificing accuracy. Our code is available at https://github.com/QinnanCai0115/role-factorized-search.","short_abstract":"Large language model based search agents increasingly adopt multi-agent architectures in which a main agent decomposes a complex question into sub-queries and dispatches them to parallel sub-agents. However, existing systems instantiate all roles from a single model of identical scale, leaving open how model capacity s...","url_abs":"https://arxiv.org/abs/2607.07548","url_pdf":"https://arxiv.org/pdf/2607.07548v1","authors":"[\"Qinnan Cai\",\"Yibo Zhao\",\"Xiang Li\"]","published":"2026-07-08T15:46:48Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Language Model\"]","has_code":false,"code_links":[{"ID":614058,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-09T01:07:32.349475501Z","DeletedAt":null,"paper_id":6138332,"paper_url":"https://arxiv.org/abs/2607.07548","paper_title":"Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?","repo_url":"https://github.com/QinnanCai0115/role-factorized-search","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}