[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85605-en":3,"doc-seo-85605-105":30,"detail-sidebar-cat-0-en-105":83},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85605,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","AI Research Agents Narrow Scientific Exploration","AI research agents are increasingly used to support large-scale AI-assisted scientific discovery, but their influence on how far science is explored remains unclear. This study tests whether AI-generated ideas broaden exploration or primarily reinforce existing work. Using five agent frameworks and five large language models, it generates 219,655 ideas across scientific fields. Four consistent patterns show stronger concentration around local literature, weaker alignment with future research, and placement in lower-impact regions, limiting broad exploration.","arXiv :2605 .27905v2 [ cs .CL] 11 Jul 2026  \nAI Research Agents Narrow Scientific Exploration  \nYixuan Tang 1 and Yi Yang 1*  \n1* ISOM, The Hong Kong University of Science and Technology.  \n*Corresponding author(s). E-mail(s): [imyiyang@ust.hk](imyiyang@ust.hk) ; Contributing authors: [ytangch@connect.ust.hk](ytangch@connect.ust.hk) ;  \nAbstract  \nAI research agents now support large-scale AI-assisted scientific discovery. We examine whether AI-generated ideas broaden scientific exploration or primarily reinforce existing work. Using five agent frameworks and five large language models, we generate 219,655 ideas for different scientific fields. Across experiments, four consistent patterns emerge. First, AI-generated ideas are more concentrated than human-authored papers within the same research area. Second, they remain much closer to starting literature than later human follow-on work does. Third, AIgenerated ideas align less with future human research. Last, AI-generated ideas are located in lower-impact regions of the historical scientific landscape. Overall, current AI research agents appear better suited to local elaboration than to broadening scientific exploration.  \nKeywords: Artificial intelligence, Agentic AI, Scientific discovery, Large language models, Science of science  \n1 Introduction  \nRecent advances in AI research agents have raised the possibility of automating scientific discovery. These agents can now conduct literature reviews, generate research ideas, plan experiments, run code, write papers, and iteratively explore and refine scientific hypotheses [1–4] . Importantly, these AI research agent frameworks are explicitly designed to encourage exploratory scientific ideation. Their prompts and reasoning procedures often instruct agents to generate novel, high-impact, and unconventional ideas rather than simple extensions of prior work [1–3] . As such systems become increasingly capable and accessible, they may fundamentally reshape the process of scientific discovery.  \nYet the ability to generate research ideas at scale does not necessarily imply broader scientific exploration. Scientific discovery often depends on moving beyond established directions, searching less familiar regions, and recombining prior knowledge in non-routine ways [5, 6] . Existing evaluations of AI research agents mainly assess whether individual ideas are interesting, novel, feasible, or executable [7, 8], but reveal much less about how repeated AI-assisted ideation may shape the broader landscape of scientific exploration. This raises a broader question: do AI research agents broaden scientific exploration?  \nTo study this question, we construct research areas from the scientific literature across broad fields and use AI research agents to generate ideas from shared seed papers within each research area. Specifically, using papers published between 2020 and 2025 from the Semantic Scholar Academic Graph as seed literature, we use advanced AI research-agent frameworks, including AIScientist [1], ResearchAgent [2], AgentLaboratory [3], and Co-Scientist [9], together with five LLMs to generate complete scientific research ideas, including both research questions and methods. In total, we analyze 219,655 valid AI-generated research ideas spanning 12 broad scientific fields and 155 research areas. Throughout the ideation process, all evaluated AI agent frameworks are explicitly instructed to explore novel research directions beyond the seed literature. The AI  \n(a) Citation-defined research areas (b) AI ideation from seed papers (c) Compare idea distributions  \nBiology Cryo-EM  \nBiology Cryo-EM Physics Heavy-ion  \nSeed literature  AI-generated ideas Follow-on human papers  \nFig. 1 Overview of the study design. We first construct research areas from the Semantic Scholar corpus, use AIresearch agents to generate scientific ideas from prior literature in those areas, and compare the resulting ideas against human-authored papers.  \nagent fram","cbCaibF1wJbk82zO","https://ap.wps.com/l/cbCaibF1wJbk82zO","pdf",2305457,3,1,32,"English","en",105,"# Introduction\n# Generating Scientific Ideas with AI Agents","[{\"question\":\"What are the main findings about how AI-generated ideas differ from human follow-on work?\",\"answer\":\"Across evaluations, AI-generated ideas are more concentrated within their research areas, remain closer to starting literature, align less with future human research frontiers, and are linked to lower-citation regions than later human follow-on work.\"}]",1784204866,81,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":28},"ai-research-agents-narrow-scientific-exploration","",{"@graph":36,"@context":77},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/ai-research-agents-narrow-scientific-exploration/85605/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What are the main findings about how AI-generated ideas differ from human follow-on work?","Question",{"text":75,"@type":76},"Across evaluations, AI-generated ideas are more concentrated within their research areas, remain closer to starting literature, align less with future human research frontiers, and are linked to lower-citation regions than later human follow-on work.","Answer","https://schema.org",{"og:url":51,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]