{"id":"https://openalex.org/W4414854692","doi":"https://doi.org/10.48550/arxiv.2505.19253","title":"DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research","display_name":"DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research","publication_year":2025,"publication_date":"2025-05-25","ids":{"openalex":"https://openalex.org/W4414854692","doi":"https://doi.org/10.48550/arxiv.2505.19253"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.19253","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.19253","pdf_url":"https://arxiv.org/pdf/2505.19253","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.19253","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Coelho, Jo\u00e3o","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["PT","US"],"is_corresponding":false,"raw_author_name":"Coelho, Jo\u00e3o","raw_affiliation_strings":["Carnegie Mellon University","IST and INESC - ID"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"IST and INESC - ID","institution_ids":["https://openalex.org/I121345201"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ning, Jingjie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ning, Jingjie","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018271494","display_name":"Jingyuan He","orcid":"https://orcid.org/0000-0002-3116-7554","observed_orcids":["https://orcid.org/0000-0002-3116-7554"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He, Jingyuan","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140725042","display_name":"Kangrui Mao","orcid":"https://orcid.org/0009-0001-5601-4159","observed_orcids":["https://orcid.org/0009-0001-5601-4159"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mao, Kangrui","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114701275","display_name":"Abhijay Sai Paladugu","orcid":"https://orcid.org/0009-0006-4840-5965","observed_orcids":["https://orcid.org/0009-0006-4840-5965"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paladugu, Abhijay","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119861769","display_name":"Pranav Setlur","orcid":"https://orcid.org/0009-0000-7446-9520","observed_orcids":["https://orcid.org/0009-0000-7446-9520"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Setlur, Pranav","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jin, Jiahe","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jin, Jiahe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009879041","display_name":"Jamie Callan","orcid":"https://orcid.org/0000-0002-1211-7754","observed_orcids":["https://orcid.org/0000-0002-1211-7754"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Callan, Jamie","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002705720","display_name":"Jo\u00e3o Magalh\u00e3es","orcid":"https://orcid.org/0000-0001-6290-5719","observed_orcids":["https://orcid.org/0000-0001-6290-5719"]},"institutions":[{"id":"https://openalex.org/I4405257428","display_name":"Laborat\u00f3rio para a Ci\u00eancia da Computa\u00e7\u00e3o e Inform\u00e1tica","ror":"https://ror.org/058e2tg06","country_code":"PT","type":"facility","lineage":["https://openalex.org/I4405257428","https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Magalh\u00e3es, Jo\u00e3o","raw_affiliation_strings":["NOVA LINCS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA LINCS","institution_ids":["https://openalex.org/I4405257428"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055101594","display_name":"Bruno Martins","orcid":"https://orcid.org/0000-0002-3856-2936","observed_orcids":["https://orcid.org/0000-0002-3856-2936"]},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Martins, Bruno","raw_affiliation_strings":["IST and INESC - ID"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IST and INESC - ID","institution_ids":["https://openalex.org/I121345201"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102363883","display_name":"Chenyan Xiong","orcid":"https://orcid.org/0000-0002-0392-4183","observed_orcids":["https://orcid.org/0000-0002-0392-4183"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiong, Chenyan","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":71,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9955999851226807,"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":0.9955999851226807,"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":0.0026000000070780516,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.0005000000237487257,"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/benchmarking","display_name":"benchmarking","score":0.4729999899864197},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.9559999704360962},{"id":"https://openalex.org/keywords/reporting-quality","display_name":"reporting quality","score":0.5929999947547913},{"id":"https://openalex.org/keywords/dense-retrievers","display_name":"dense retrievers","score":0.5759999752044678},{"id":"https://openalex.org/keywords/approximate-nearest-neighbor-search","display_name":"approximate nearest neighbor search","score":0.9150000214576721}],"concepts":[{"id":"https://openalex.org/C167981075","wikidata":"https://www.wikidata.org/wiki/Q2667186","display_name":"Sandbox (software development)","level":2,"score":0.8471999764442444},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7960000038146973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178999781608582},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5486999750137329},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5289000272750854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49160000681877136},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4348999857902527},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4007999897003174},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3831000030040741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37229999899864197},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25600001215934753},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.19253","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.19253","pdf_url":"https://arxiv.org/pdf/2505.19253","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.2505.19253","doi":"https://doi.org/10.48550/arxiv.2505.19253","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.19253","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:2505.19253","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.19253","pdf_url":"https://arxiv.org/pdf/2505.19253","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/W4414854692.pdf","grobid_xml":"https://content.openalex.org/works/W4414854692.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7168300957","https://openalex.org/W4416176141","https://openalex.org/W7092298889","https://openalex.org/W4416399833","https://openalex.org/W7168405860","https://openalex.org/W4416189150","https://openalex.org/W7154751841","https://openalex.org/W7171922118","https://openalex.org/W7124180632","https://openalex.org/W7124300113"],"abstract_inverted_index":{"Deep":[0],"research":[1,67,111,116],"systems":[2,146],"represent":[3],"an":[4,50],"emerging":[5],"class":[6],"of":[7],"agentic":[8],"information":[9,135],"retrieval":[10,137],"methods":[11],"that":[12,53,145,181],"generate":[13],"comprehensive":[14],"and":[15,34,78,85,107,139],"well-supported":[16],"reports":[17],"to":[18,39,130,152,189],"complex":[19],"queries.":[20],"However,":[21],"most":[22],"existing":[23],"frameworks":[24],"rely":[25],"on":[26,168],"dynamic":[27],"commercial":[28,98,155,190],"search":[29,57,89,170],"APIs,":[30,156],"which":[31],"pose":[32],"reproducibility":[33],"transparency":[35],"challenges":[36],"in":[37],"addition":[38],"their":[40],"cost.":[41],"To":[42,113],"address":[43],"these":[44],"limitations,":[45],"we":[46,119],"introduce":[47],"\\textsc{DeepResearchGym}":[48],"as":[49],"open-source":[51],"sandbox":[52,186],"combines":[54],"a":[55,60,81],"reproducible":[56],"API":[58,70],"with":[59,125,133,157],"rigorous":[61],"evaluation":[62,163],"protocol":[63],"for":[64,110,177],"benchmarking":[65],"deep":[66,115],"systems.":[68],"The":[69],"indexes":[71],"large-scale":[72],"public":[73],"web":[74],"corpora,":[75],"namely":[76],"ClueWeb22":[77],"FineWeb,":[79],"using":[80,154],"state-of-the-art":[82],"dense":[83],"retriever":[84],"approximate":[86],"nearest":[87],"neighbor":[88],"via":[90],"DiskANN.":[91],"It":[92],"achieves":[93],"lower":[94],"latency":[95],"than":[96],"popular":[97],"APIs":[99],"while":[100],"ensuring":[101],"stable":[102],"document":[103],"rankings":[104,159],"across":[105,162],"runs,":[106],"is":[108],"free":[109],"use.":[112],"evaluate":[114],"systems'":[117],"outputs,":[118],"extend":[120],"the":[121,174,185],"Researchy":[122],"Questions":[123],"benchmark":[124],"automatic":[126],"metrics":[127],"through":[128],"LLM-as-a-judge":[129],"measure":[131],"alignment":[132],"users'":[134],"needs,":[136],"faithfulness,":[138],"report":[140],"quality.":[141],"Experimental":[142],"results":[143],"show":[144],"integrated":[147],"with~\\textsc{DeepResearchGym}":[148],"achieve":[149],"performance":[150,158],"comparable":[151],"those":[153],"remaining":[160],"consistent":[161],"metrics.":[164],"A":[165],"case":[166],"study":[167],"short-answer":[169],"agents":[171],"further":[172],"demonstrates":[173],"sandbox's":[175],"utility":[176],"cost-effective":[178],"training,":[179],"showing":[180],"models":[182],"trained":[183],"within":[184],"can":[187],"generalize":[188],"search.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":55},{"year":2025,"cited_by_count":16}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}