{"id":"https://openalex.org/W4416692425","doi":"https://doi.org/10.48550/arxiv.2509.01396","title":"DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks","display_name":"DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4416692425","doi":"https://doi.org/10.48550/arxiv.2509.01396"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.01396","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.01396","pdf_url":"https://arxiv.org/pdf/2509.01396","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.01396","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wan, Haiyuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Haiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070310624","display_name":"Chen Yang","orcid":"https://orcid.org/0000-0002-7688-9278","observed_orcids":["https://orcid.org/0000-0002-7688-9278","https://orcid.org/0009-0007-2438-8010"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yu, Junchi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Junchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111087680","display_name":"M Tu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Meiqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lu, Jiaxuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Jiaxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031481749","display_name":"Di Yu","orcid":"https://orcid.org/0000-0002-5298-5812","observed_orcids":["https://orcid.org/0000-0002-5298-5812"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Di","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cao, Jianbao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Jianbao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gao, Ben","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Ben","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xie, Jiaqing","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Jiaqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041286681","display_name":"Aoran Wang","orcid":"https://orcid.org/0000-0001-7721-2982","observed_orcids":["https://orcid.org/0000-0001-7721-2982"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Aoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453359","display_name":"Wenlong Zhang","orcid":"https://orcid.org/0009-0009-7490-3660","observed_orcids":["https://orcid.org/0009-0009-7490-3660","https://orcid.org/0009-0007-4897-1008"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109615038","display_name":"Philip H.S. Torr","orcid":"https://orcid.org/0000-0001-5545-7217","observed_orcids":["https://orcid.org/0000-0001-5545-7217"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Torr, Philip","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112578541","display_name":"Dongzhan Zhou","orcid":"https://orcid.org/0000-0001-6568-5440","observed_orcids":["https://orcid.org/0000-0001-6568-5440","https://orcid.org/0009-0007-2513-9585"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Dongzhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6172000169754028,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6172000169754028,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.09309999644756317,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.026599999517202377,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7279999852180481},{"id":"https://openalex.org/keywords/scientific-seminars","display_name":"academic seminars","score":0.7229999899864197},{"id":"https://openalex.org/keywords/literature-synthesis","display_name":"literature synthesis","score":0.609000027179718},{"id":"https://openalex.org/keywords/benchmark-design","display_name":"benchmark design","score":0.5270000100135803},{"id":"https://openalex.org/keywords/data-leakage","display_name":"data leakage","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6948999762535095},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6662999987602234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5989999771118164},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5443999767303467},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.510200023651123},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4417000114917755},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C153876917","wikidata":"https://www.wikidata.org/wiki/Q899704","display_name":"Traceability","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3912000060081482},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31139999628067017},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3059999942779541},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.25209999084472656},{"id":"https://openalex.org/C3018233652","wikidata":"https://www.wikidata.org/wiki/Q101965","display_name":"Experimental research","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2509.01396","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.01396","pdf_url":"https://arxiv.org/pdf/2509.01396","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":"pmh:oai:ojs.aaai.org:article/40620","doi":null,"is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/40620","pdf_url":null,"source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2509.01396","doi":"https://doi.org/10.48550/arxiv.2509.01396","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.01396","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:2509.01396","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.01396","pdf_url":"https://arxiv.org/pdf/2509.01396","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415069437","https://openalex.org/W4416189150","https://openalex.org/W7124180632","https://openalex.org/W7154751841","https://openalex.org/W4414804651","https://openalex.org/W7166828574","https://openalex.org/W4414823918","https://openalex.org/W7140001438","https://openalex.org/W7126157955","https://openalex.org/W4414489845"],"abstract_inverted_index":{"Deep":[0],"research":[1,13,28,41,75,114,120,138],"agents":[2],"have":[3],"attracted":[4],"growing":[5],"attention":[6,47],"for":[7,164],"their":[8,27],"potential":[9],"to":[10,35],"orchestrate":[11],"multi-stage":[12],"workflows,":[14],"spanning":[15,145],"literature":[16],"synthesis,":[17],"methodological":[18],"design,":[19],"and":[20,48,70,77,152],"empirical":[21],"verification.":[22],"Despite":[23],"these":[24],"strides,":[25],"evaluating":[26],"capability":[29],"faithfully":[30],"is":[31],"rather":[32],"challenging":[33],"due":[34],"the":[36,79,117,127],"difficulty":[37],"of":[38,81,119],"collecting":[39],"frontier":[40],"questions":[42],"that":[43,65,98,158],"genuinely":[44],"capture":[45,66],"researchers'":[46],"intellectual":[49],"curiosity.":[50],"To":[51,84],"address":[52],"this":[53],"gap,":[54],"we":[55,89,130],"introduce":[56],"DeepResearch":[57,87,132,159],"Arena,":[58,88],"a":[59,91],"benchmark":[60],"grounded":[61],"in":[62],"academic":[63,143],"seminars":[64],"rich":[67],"expert":[68],"discourse":[69],"interaction,":[71],"better":[72],"reflecting":[73],"real-world":[74],"environments":[76],"reducing":[78],"risk":[80],"data":[82],"leakage.":[83],"automatically":[85],"construct":[86],"propose":[90],"Multi-Agent":[92],"Hierarchical":[93],"Task":[94],"Generation":[95],"(MAHTG)":[96],"system":[97,107],"extracts":[99],"research-worthy":[100,110],"inspirations":[101,111],"from":[102,140],"seminar":[103],"transcripts.":[104],"The":[105],"MAHTG":[106,128],"further":[108],"translates":[109],"into":[112],"high-quality":[113,137],"tasks,":[115],"ensuring":[116],"traceability":[118],"task":[121],"formulation":[122],"while":[123],"filtering":[124],"noise.":[125],"With":[126],"system,":[129],"curate":[131],"Arena":[133,160],"with":[134,168],"over":[135,141],"10,000":[136],"tasks":[139],"200":[142],"seminars,":[144],"12":[146],"disciplines,":[147],"such":[148],"as":[149],"literature,":[150],"history,":[151],"science.":[153],"Our":[154],"extensive":[155],"evaluation":[156],"shows":[157],"presents":[161],"substantial":[162],"challenges":[163],"current":[165],"state-of-the-art":[166],"agents,":[167],"clear":[169],"performance":[170],"gaps":[171],"observed":[172],"across":[173],"different":[174],"models.":[175]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2025-10-10T00:00:00"}