{"id":"https://openalex.org/W7168248013","doi":"https://doi.org/10.48550/arxiv.2607.10557","title":"UNIBROWSE: A Data-to-Agent Framework for Multimodal BrowseComp","display_name":"UNIBROWSE: A Data-to-Agent Framework for Multimodal BrowseComp","publication_year":2026,"publication_date":"2026-07-12","ids":{"openalex":"https://openalex.org/W7168248013","doi":"https://doi.org/10.48550/arxiv.2607.10557"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.10557","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.10557","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2607.10557","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140627910","display_name":"Xiyu Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Xiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140698335","display_name":"Qingwei Zong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zong, Qingwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140673374","display_name":"Zhuocheng Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Zhuocheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140587094","display_name":"Sujian Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Sujian","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.32600000500679016,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.32600000500679016,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.13660000264644623,"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":0.10790000110864639,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.6571000218391418},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5925999879837036},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.48660001158714294},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4616999924182892},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4571000039577484},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.4196999967098236},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4162999987602234},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.4156000018119812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796999990940094},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6571000218391418},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5925999879837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5099999904632568},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.426800012588501},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.10557","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.10557","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.10557","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.10557","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"BrowseComp":[1,146],"tasks":[2],"require":[3],"agents":[4],"to":[5,20,106],"combine":[6],"perception,":[7],"tool":[8],"use,":[9],"and":[10,26,43,54,61,65,98,123,127,135,170,183],"long-horizon":[11],"reasoning":[12],"over":[13,164],"dynamic":[14],"web":[15,93],"content,":[16],"challenging":[17],"their":[18],"ability":[19],"handle":[21],"compositional":[22],"structure,":[23],"open-world":[24],"uncertainty,":[25],"multimodal":[27,34,145],"integration":[28],"across":[29,154],"extended":[30],"interactions.":[31],"Crucially,":[32],"real-world":[33],"browsing":[35],"involves":[36],"three":[37,85],"distinct":[38],"information-flow":[39],"patterns:":[40],"text-only,":[41],"image-to-text,":[42],"text-to-image,":[44],"yet":[45],"existing":[46],"data":[47,72,82],"construction":[48],"methods":[49],"cover":[50],"only":[51],"the":[52,76],"text-only":[53],"image-to-text":[55],"patterns,":[56,86],"leaving":[57],"text-to-image":[58],"largely":[59],"unaddressed":[60],"limiting":[62],"agent":[63,131,140,174],"generality":[64],"robustness.":[66],"We":[67],"introduce":[68],"UNIBROWSE,":[69],"a":[70,100,129],"unified":[71],"pipeline":[73],"that":[74],"for":[75,95,110],"first":[77],"time":[78],"simultaneously":[79],"generates":[80],"training":[81],"covering":[83],"all":[84],"augments":[87],"curated":[88],"knowledge":[89],"graphs":[90],"with":[91],"live":[92],"retrieval":[94],"improved":[96],"fidelity,":[97],"introduces":[99],"novel":[101],"metric":[102],"of":[103,152,161],"exploration":[104],"degree":[105],"filter":[107],"low-signal":[108],"instances":[109],"efficient":[111],"reinforcement":[112],"learning.":[113],"Through":[114],"this":[115],"pipeline,":[116],"we":[117],"produce":[118],"high-quality":[119],"cold-start":[120],"tool-use":[121],"trajectories":[122],"exploration-rich":[124],"QA":[125],"pairs,":[126],"train":[128],"35B-scale":[130],"via":[132],"supervised":[133],"fine-tuning":[134],"exploration-aware":[136],"RL.The":[137],"resulting":[138],"UNIBROWSE":[139],"achieves":[141],"state-of-the-art":[142],"performance":[143],"on":[144],"benchmarks,":[147],"attaining":[148],"an":[149,159],"average":[150],"accuracy":[151],"54.4":[153],"five":[155],"diverse":[156],"benchmarks":[157],"--":[158,169],"improvement":[160],"10.5":[162],"points":[163],"its":[165],"base":[166],"model":[167],"Qwen3.5-35B-A3B":[168],"surpassing":[171],"serveral":[172],"closed-source":[173],"workflows":[175],"such":[176],"as":[177],"GPT-5":[178],"(42.9),":[179],"Gemini-2.5":[180,184],"Pro":[181],"(44.8),":[182],"Flash":[185],"(41.3).":[186]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-15T00:00:00"}