{"id":"https://openalex.org/W7155416132","doi":"https://doi.org/10.48550/arxiv.2604.19859","title":"DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data","display_name":"DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155416132","doi":"https://doi.org/10.48550/arxiv.2604.19859"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.19859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19859","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.19859","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125675442","display_name":"Veuns-Team","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Venus Team","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134372800","display_name":"Sunhao Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Sunhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134382178","display_name":"Yong Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Yong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134395019","display_name":"Jinzhen Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Jinzhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134390299","display_name":"Yusheng Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Yusheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134431929","display_name":"Guoqing Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Guoqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134440928","display_name":"Xiaofeng Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xiaofeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038388256","display_name":"Yuqi Zhou","orcid":"https://orcid.org/0000-0003-4988-7637"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yuqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134424973","display_name":"Shuo su Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Shuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134396590","display_name":"Zhenzhe Ying","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying, Zhenzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134444394","display_name":"Zhanwei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhanwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009885446","display_name":"Changhua Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Changhua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134436018","display_name":"Weiqiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Weiqiang","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/T10036","display_name":"Advanced Neural Network Applications","score":0.13349999487400055,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.13349999487400055,"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"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.11670000106096268,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.08649999648332596,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.666100025177002},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6656000018119812},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5295000076293945},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5220999717712402},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5097000002861023},{"id":"https://openalex.org/keywords/frontier","display_name":"Frontier","score":0.5038999915122986},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4778999984264374},{"id":"https://openalex.org/keywords/recipe","display_name":"Recipe","score":0.4147999882698059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6970000267028809},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.666100025177002},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6656000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6234999895095825},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5295000076293945},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5097000002861023},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4778999984264374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4713999927043915},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.448199987411499},{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3698999881744385},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C15189868","wikidata":"https://www.wikidata.org/wiki/Q534685","display_name":"Long tail","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2574999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.19859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19859","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.19859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19859","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5334600210189819,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Edge-scale":[0],"deep":[1,34,54,119,172,229],"research":[2,35,55,120,173,226,230],"agents":[3,128,191],"based":[4,140],"on":[5,62,117,134,141,157,170,227],"small":[6,33,127,204],"language":[7],"models":[8,166,205],"are":[9],"attractive":[10],"for":[11,57,126],"real-world":[12],"deployment":[13,201],"due":[14],"to":[15,29,82,96,112,180,223],"their":[16],"advantages":[17],"in":[18,129,212],"cost,":[19],"latency,":[20],"and":[21,45,100,136,144,151,206,220],"privacy.":[22],"In":[23,72,102],"this":[24,130,213],"work,":[25],"we":[26,76,106,132],"study":[27],"how":[28],"train":[30],"a":[31,51],"strong":[32,195],"agent":[36,56],"under":[37,167],"limited":[38],"open-data":[39],"by":[40],"improving":[41],"both":[42,199],"data":[43,46,89,98],"quality":[44,99],"utilization.":[47,101],"We":[48,215],"present":[49],"DR-Venus,":[50],"frontier":[52],"4B":[53,190],"edge-scale":[58,228],"deployment,":[59],"built":[60],"entirely":[61,156],"open":[63],"data.":[64],"Our":[65,185],"training":[66],"recipe":[67],"consists":[68],"of":[69,93,203,209],"two":[70],"stages.":[71],"the":[73,103,178,200,207],"first":[74],"stage,":[75,105],"use":[77],"agentic":[78,85,108,165],"supervised":[79],"fine-tuning":[80],"(SFT)":[81],"establish":[83],"basic":[84],"capability,":[86],"combining":[87],"strict":[88],"cleaning":[90],"with":[91],"resampling":[92],"long-horizon":[94,118],"trajectories":[95],"improve":[97,114],"second":[104],"apply":[107],"reinforcement":[109],"learning":[110],"(RL)":[111],"further":[113,186],"execution":[115],"reliability":[116],"tasks.":[121],"To":[122],"make":[123],"RL":[124],"effective":[125],"setting,":[131],"build":[133],"IGPO":[135],"design":[137],"turn-level":[138,152],"rewards":[139],"information":[142],"gain":[143],"format-aware":[145],"regularization,":[146],"thereby":[147],"enhancing":[148],"supervision":[149],"density":[150],"credit":[153],"assignment.":[154],"Built":[155],"roughly":[158],"10K":[159],"open-data,":[160],"DR-Venus-4B":[161],"significantly":[162],"outperforms":[163],"prior":[164],"9B":[168],"parameters":[169],"multiple":[171],"benchmarks,":[174],"while":[175],"also":[176],"narrowing":[177],"gap":[179],"much":[181],"larger":[182],"30B-class":[183],"systems.":[184],"analysis":[187],"shows":[188],"that":[189],"already":[192],"possess":[193],"surprisingly":[194],"performance":[196],"potential,":[197],"highlighting":[198],"promise":[202],"value":[208],"test-time":[210],"scaling":[211],"setting.":[214],"release":[216],"our":[217],"models,":[218],"code,":[219],"key":[221],"recipes":[222],"support":[224],"reproducible":[225],"agents.":[231]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-24T00:00:00"}