{"id":"https://openalex.org/W7168248013","doi":"https://doi.org/10.18653/2026.findings-emnlp.667","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":"2026-01-01","ids":{"openalex":"https://openalex.org/W7168248013","doi":"https://doi.org/10.18653/2026.findings-emnlp.667"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.667","doi":"https://doi.org/10.18653/2026.findings-emnlp.667","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.667","pdf_url":"https://aclanthology.org/2026.findings-emnlp.667.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.667.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124773626","display_name":"Xiyu Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiyu Wei","raw_affiliation_strings":["School of Software and Microelectronics , Peking University","State Key Laboratory for Multimedia Information Processing , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics , Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"State Key Laboratory for Multimedia Information Processing , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140698335","display_name":"Qingwei Zong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingwei Zong","raw_affiliation_strings":["School of Computer Science , Peking University","State Key Laboratory for Multimedia Information Processing , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"State Key Laboratory for Multimedia Information Processing , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140673374","display_name":"Zhuocheng Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuocheng Yu","raw_affiliation_strings":["School of Computer Science , Peking University","State Key Laboratory for Multimedia Information Processing , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"State Key Laboratory for Multimedia Information Processing , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160093736","display_name":"Feng Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Zhang","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153676404","display_name":"Kai Jia","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Jia","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160113166","display_name":"Sujian Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sujian Li","raw_affiliation_strings":["School of Computer Science , Peking University","State Key Laboratory for Multimedia Information Processing , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"State Key Laboratory for Multimedia Information Processing , Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53602174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14007","last_page":"14023"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5199999809265137,"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":0.5199999809265137,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.32910001277923584,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.07999999821186066,"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/training-data-generation","display_name":"training data generation","score":0.6629999876022339},{"id":"https://openalex.org/keywords/knowledge-graph-enrichment","display_name":"knowledge graph augmentation","score":0.6349999904632568},{"id":"https://openalex.org/keywords/long-horizon-reasoning","display_name":"long-horizon reasoning","score":0.7360000014305115}],"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":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.667","doi":"https://doi.org/10.18653/2026.findings-emnlp.667","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.667","pdf_url":"https://aclanthology.org/2026.findings-emnlp.667.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2607.10557","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.10557","pdf_url":"https://arxiv.org/pdf/2607.10557","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2607.10557","doi":"https://doi.org/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,"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":"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"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.667","doi":"https://doi.org/10.18653/2026.findings-emnlp.667","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.667","pdf_url":"https://aclanthology.org/2026.findings-emnlp.667.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3336050986","display_name":null,"funder_award_id":"62476010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4128466783","display_name":null,"funder_award_id":"92470205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7168248013.pdf","grobid_xml":"https://content.openalex.org/works/W7168248013.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414530236","https://openalex.org/W7129059347","https://openalex.org/W7133517971","https://openalex.org/W4412888655","https://openalex.org/W7079299863","https://openalex.org/W7131862632","https://openalex.org/W7139036837","https://openalex.org/W7133354148","https://openalex.org/W7064474751","https://openalex.org/W7124248943"],"abstract_inverted_index":{"Multimodal":[0],"BrowseComp":[1,143],"tasks":[2],"require":[3],"agents":[4],"to":[5,20,104],"combine":[6],"perception,":[7],"tool":[8],"use,":[9],"and":[10,26,42,53,60,64,96,120,124,132,173,180],"longhorizon":[11],"reasoning":[12],"over":[13,159],"dynamic":[14],"web":[15,91],"content,":[16],"challenging":[17],"their":[18],"ability":[19],"handle":[21],"compositional":[22],"structure,":[23],"open-world":[24],"uncertainty,":[25],"multimodal":[27,33,142],"integration":[28],"across":[29,151],"extended":[30],"interactions.Crucially,":[31],"real-world":[32],"browsing":[34],"involves":[35],"three":[36,83],"distinct":[37],"information-flow":[38],"patterns:":[39],"text-only,":[40],"image-to-text,":[41],"textto-image,":[43],"yet":[44],"existing":[45],"data":[46,70,80],"construction":[47],"methods":[48],"cover":[49],"only":[50],"the":[51,74],"text-only":[52],"image-to-text":[54],"patterns,":[55,84],"leaving":[56],"text-to-image":[57],"largely":[58],"unaddressed":[59],"limiting":[61],"agent":[62,128,137,166],"generality":[63],"robustness.We":[65],"introduce":[66],"UNIBROWSE,":[67],"a":[68,98,126],"unified":[69],"pipeline":[71],"that":[72],"for":[73,93,108],"first":[75],"time":[76],"simultaneously":[77],"generates":[78],"training":[79],"covering":[81],"all":[82],"augments":[85],"curated":[86],"knowledge":[87],"graphs":[88],"with":[89],"live":[90],"retrieval":[92],"improved":[94],"fidelity,":[95],"introduces":[97],"novel":[99],"metric":[100],"of":[101,149,156],"exploration":[102],"degree":[103],"filter":[105],"low-signal":[106],"instances":[107],"efficient":[109],"reinforcement":[110],"learning.Through":[111],"this":[112],"pipeline,":[113],"we":[114],"produce":[115],"high-quality":[116],"cold-start":[117],"tool-use":[118],"trajectories":[119],"explorationrich":[121],"QA":[122],"pairs,":[123],"train":[125],"35B-scale":[127],"via":[129],"supervised":[130],"fine-tuning":[131],"explorationaware":[133],"RL.The":[134],"resulting":[135],"UNIBROWSE":[136],"achieves":[138],"state-of-the-art":[139],"performance":[140],"on":[141],"benchmarks,":[144],"attaining":[145],"an":[146],"average":[147],"accuracy":[148],"54.4":[150],"five":[152],"diverse":[153],"benchmarks-an":[154],"improvement":[155],"10.5":[157],"points":[158],"its":[160],"base":[161],"model":[162],"Qwen3.5-35B-A3Bandsurpassing":[163],"serveral":[164],"closed-source":[165],"workflows":[167],"such":[168],"as":[169],"GPT-5":[170,187],"(42.9),Gemini-2.5Pro":[171],"(44.8),":[172],"Gemini-2.5Flash":[174],"(41.3).We":[175],"will":[176],"release":[177],"our":[178],"code":[179],"dataset":[181],"at":[182],"https:":[183],"//github.com/lemon-prog123/UniBrowse.":[184],"UniBrowse-35B-A3BGemini-2.5":[185],"Pro":[186],"Kimi":[188],"K2.5":[189],"Qwen3.":[190]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-07-15T00:00:00"}