[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84242-en":3,"doc-seo-84242-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},84242,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents","Large language model based search agents increasingly use multi-agent architectures where a main agent decomposes a question into sub-queries and delegates them to parallel sub-agents. Existing systems typically instantiate all roles from identical-scale models, leaving uncertainty about how capacity should be allocated. This work factorizes hierarchical search into delegation, execution, and a fixed answer-generation control role, then runs controlled capacity sweeps on multi-hop QA benchmarks.","arXiv :2607 .07548v 1 [ cs .CL] 8 Jul 2026  \nTHINK BIG, SEARCH SMALL: WHERE CAPACITY MATTERS IN HIERARCHICAL SEARCH AGENTS?  \nQinnan CaiYibo Zhao∗& Xiang Li † School of Data Science and Engineering East China Normal University  \nABSTRACT  \nLarge 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  \n8.6 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.  \nThese 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/](https://github.com/QinnanCai0115/)[ ](https://github.com/QinnanCai0115/)[role-factorized-search](role-factorized-search.)[.](role-factorized-search.)  \n1 INTRODUCTION  \nLarge language model (LLM) based search agents have rapidly emerged as a central topic in the LLM community (Singh et al., 2025; Li et al.; Shi et al., 2025; Team et al., 2026) . By interleaving reasoning with retrieval, modern search agents can autonomously decompose a question, issue a sequence of queries, and synthesize evidence scattered across multiple retrieved documents (Jin et al., 2025; Trivedi et al., 2023; Yao et al., 2022; Li et al., 2025b; Jiang et al., 2023) . As both model capability and task ambition scale up, the scope of search keeps expanding from single-hop factoid questions (Mallen et al., 2023) to complex multi-hop questions whose answers must be composed from many pieces of evidence (Yang et al., 2018; Ho et al., 2020; Trivedi et al., 2022; Press et al., 2023), making agentic search a demanding and informative testbed for LLM-based agents.  \nTo date, the majority of search agents follow a single-agent route: one model is responsible for planning, issuing queries, reading retrieved documents, and producing the final answer, all within a single shared context (Jin et al., 2025; Song et al., 2025; Gao et al., 2025) . This design is conceptually simple and has proven highly effective (Singh et al., 2025; Li et al.) . By construction, every retrieved passage and every intermediate observation accumulates in the same context window.  \nHowever, as the number of hops and retrieval rounds grows, this context grows with it: passages that are each only locally relevant to one sub-question pile up alongside the original question and the agent’s own plan (Du et al., 2025; Liu et al., 2024) . The single model must therefore act as  \n∗Equal contribution.  \n†Corresponding author: [xiangli@dase.ecnu.edu.cn](xiangli@dase.ecnu.edu.cn).  \nplanner, reader, and synthesizer over a context that keeps expanding, a tension that grows more pronounced as questions require more reasoning hops and retrieval rounds.  \nA complementary route addresses this tension through multi-agent collaboration. Instead ","cbCaip6gNLt1NFeN","https://ap.wps.com/l/cbCaip6gNLt1NFeN","pdf",3378972,1,21,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What core problem does the paper address in hierarchical search agents?\",\"answer\":\"The paper studies how to allocate model capacity across different roles in hierarchical search agents rather than using identical-scale models for all roles.\"},{\"question\":\"How are roles factorized in the proposed hierarchical search framework?\",\"answer\":\"Hierarchical search is split into a delegation role for task decomposition, an execution role for retrieval and evidence extraction, and an answer generation role kept fixed as a control.\"},{\"question\":\"What do the controlled capacity experiments show about which role is the bottleneck?\",\"answer\":\"Capacity sensitivity is asymmetric: scaling the delegation role improves exact match substantially more than scaling the execution role, indicating decomposition as the capability bottleneck.\"}]",1784194304,53,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"think-big-search-small-where-capacity-matters-in-hierarchical-search-agents","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/think-big-search-small-where-capacity-matters-in-hierarchical-search-agents/84242/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What core problem does the paper address in hierarchical search agents?","Question",{"text":74,"@type":75},"The paper studies how to allocate model capacity across different roles in hierarchical search agents rather than using identical-scale models for all roles.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How are roles factorized in the proposed hierarchical search framework?",{"text":79,"@type":75},"Hierarchical search is split into a delegation role for task decomposition, an execution role for retrieval and evidence extraction, and an answer generation role kept fixed as a control.",{"name":81,"@type":72,"acceptedAnswer":82},"What do the controlled capacity experiments show about which role is the bottleneck?",{"text":83,"@type":75},"Capacity sensitivity is asymmetric: scaling the delegation role improves exact match substantially more than scaling the execution role, indicating decomposition as the capability bottleneck.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]