{"id":"https://openalex.org/W4417525709","doi":"https://doi.org/10.52202/085713-4011","title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","display_name":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4417525709","doi":"https://doi.org/10.52202/085713-4011"},"language":"en","primary_location":{"id":"doi:10.52202/085713-4011","doi":"https://doi.org/10.52202/085713-4011","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-4011","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.21776","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100667928","display_name":"Xiaoxi Li","orcid":"https://orcid.org/0000-0002-2153-5608","observed_orcids":["https://orcid.org/0000-0002-2153-5608"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxi Li","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000165016","display_name":"Jiajie Jin","orcid":"https://orcid.org/0009-0006-4808-1534","observed_orcids":["https://orcid.org/0009-0006-4808-1534","https://orcid.org/0009-0007-6711-567X"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajie Jin","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008320336","display_name":"Guanting Dong","orcid":"https://orcid.org/0000-0002-2318-0281","observed_orcids":["https://orcid.org/0000-0002-2318-0281"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanting Dong","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010274969","display_name":"Hongjin Qian","orcid":"https://orcid.org/0000-0003-4011-5673","observed_orcids":["https://orcid.org/0000-0003-4011-5673"]},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjin Qian","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046536024","display_name":"Yongkang Wu","orcid":"https://orcid.org/0000-0002-7352-3465","observed_orcids":["https://orcid.org/0000-0002-7352-3465"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongkang Wu","raw_affiliation_strings":["Huawei Technologies Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025631695","display_name":"Ji-Rong Wen","orcid":"https://orcid.org/0000-0002-9777-9676","observed_orcids":["https://orcid.org/0000-0002-9777-9676"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji-Rong Wen","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007186741","display_name":"Yutao Zhu","orcid":"https://orcid.org/0000-0002-9432-3251","observed_orcids":["https://orcid.org/0000-0002-9432-3251"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutao Zhu","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010558184","display_name":"Zhicheng Dou","orcid":"https://orcid.org/0000-0002-9781-948X","observed_orcids":["https://orcid.org/0000-0002-9781-948X"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Dou","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.2848,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.97929362,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"133164","last_page":"133204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6977999806404114,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6977999806404114,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.22779999673366547,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.018799999728798866,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-reasoning-models","display_name":"large reasoning models","score":0.9660000205039978},{"id":"https://openalex.org/keywords/deep-research-agents","display_name":"deep research agents","score":0.7519999742507935},{"id":"https://openalex.org/keywords/web-search","display_name":"web search","score":0.5809999704360962},{"id":"https://openalex.org/keywords/website-navigation","display_name":"web navigation","score":0.7580000162124634},{"id":"https://openalex.org/keywords/report-generation","display_name":"report generation","score":0.6489999890327454},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.36899998784065247},{"id":"https://openalex.org/keywords/direct-preference-optimization","display_name":"direct preference optimization","score":0.7929999828338623},{"id":"https://openalex.org/keywords/long-horizon-reasoning","display_name":"long-horizon reasoning","score":0.8460000157356262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019999861717224},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5001000165939331},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45010000467300415},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3407999873161316},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.32589998841285706},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.32260000705718994},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/085713-4011","doi":"https://doi.org/10.52202/085713-4011","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-4011","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.21776","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.21776","pdf_url":"https://arxiv.org/pdf/2504.21776","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.21776","doi":"https://doi.org/10.48550/arxiv.2504.21776","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.21776","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.21776","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.21776","pdf_url":"https://arxiv.org/pdf/2504.21776","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417525709.pdf","grobid_xml":"https://content.openalex.org/works/W4417525709.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7128370696","https://openalex.org/W4415335984","https://openalex.org/W4412889788","https://openalex.org/W4415250073","https://openalex.org/W6979265748","https://openalex.org/W4416036988","https://openalex.org/W4416768581","https://openalex.org/W7171922118","https://openalex.org/W4416037139","https://openalex.org/W4416683608"],"abstract_inverted_index":{"Large":[0],"reasoning":[1,12,70,140],"models":[2],"(LRMs),":[3],"such":[4],"as":[5],"OpenAI-o1":[6],"and":[7,28,65,85,111,146,159,168,179],"DeepSeek-R1,":[8],"demonstrate":[9,152],"impressive":[10],"long-horizon":[11],"capabilities.":[13],"However,":[14],"their":[15,22,30],"reliance":[16],"on":[17,24,138],"static":[18],"internal":[19],"knowledge":[20,93],"limits":[21],"performance":[23],"complex,":[25],"knowledge-intensive":[26],"tasks":[27,150],"hinders":[29],"ability":[31],"to":[32,56,81,105],"produce":[33],"comprehensive":[34],"research":[35,51,120,182],"reports":[36,67],"requiring":[37],"synthesis":[38],"of":[39],"diverse":[40],"web":[41,63,90],"information.":[42],"To":[43,117],"address":[44],"this,":[45],"we":[46,123],"propose":[47],"WebThinker,":[48],"a":[49,74],"deep":[50,181],"agent":[52],"that":[53,153],"empowers":[54],"LRMs":[55,80],"autonomously":[57],"search":[58],"the":[59,69,89,103,174],"web,":[60],"navigate":[61],"among":[62],"pages,":[64],"draft":[66],"during":[68],"process.":[71],"WebThinker":[72,154],"integrates":[73],"Deep":[75],"Web":[76],"Explorer":[77],"module,":[78],"enabling":[79],"dynamically":[82],"search,":[83],"navigate,":[84],"extract":[86],"information":[87,109],"from":[88],"when":[91],"encountering":[92],"gaps.":[94],"It":[95],"also":[96],"employs":[97],"an":[98,125],"Autonomous":[99],"Think-Search-and-Draft":[100],"strategy,":[101],"allowing":[102],"model":[104],"seamlessly":[106],"interleave":[107],"reasoning,":[108],"gathering,":[110],"report":[112,148],"writing":[113],"in":[114,170],"real":[115],"time.":[116],"further":[118],"enhance":[119],"tool":[121],"utilization,":[122],"introduce":[124],"RL-based":[126],"training":[127],"strategy":[128],"via":[129],"iterative":[130],"online":[131],"Direct":[132],"Preference":[133],"Optimization":[134],"(DPO).":[135],"Extensive":[136],"experiments":[137],"complex":[139,171],"benchmarks":[141],"(GPQA,":[142],"GAIA,":[143],"WebWalkerQA,":[144],"HLE)":[145],"scientific":[147],"generation":[149],"(Glaive)":[151],"significantly":[155],"outperforms":[156],"existing":[157],"methods":[158],"strong":[160],"proprietary":[161],"systems.":[162,183],"Our":[163],"approach":[164],"enhances":[165],"LRM":[166],"reliability":[167],"applicability":[169],"scenarios,":[172],"paving":[173],"way":[175],"for":[176],"more":[177],"capable":[178],"versatile":[180],"The":[184],"code":[185],"is":[186],"available":[187],"at":[188],"https://github.com/RUC-NLPIR/WebThinker.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":7}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2025-10-10T00:00:00"}