{"id":"https://openalex.org/W4377372292","doi":"https://doi.org/10.48550/arxiv.2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","display_name":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","publication_year":2023,"publication_date":"2023-05-19","ids":{"openalex":"https://openalex.org/W4377372292","doi":"https://doi.org/10.48550/arxiv.2305.11854"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.11854","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.11854","pdf_url":"https://arxiv.org/pdf/2305.11854","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"},"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/2305.11854","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Furuta, Hiroki","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Furuta, Hiroki","raw_affiliation_strings":["Google DeepMind","The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016594236","display_name":"Kuang-Huei Lee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lee, Kuang-Huei","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057773393","display_name":"Ofir Nachum","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nachum, Ofir","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074059447","display_name":"Yutaka Matsuo","orcid":"https://orcid.org/0000-0002-2070-4393","observed_orcids":["https://orcid.org/0000-0002-2070-4393"]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Matsuo, Yutaka","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002971435","display_name":"Aleksandra Faust","orcid":"https://orcid.org/0000-0002-3268-8685","observed_orcids":["https://orcid.org/0000-0002-3268-8685"]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Faust, Aleksandra","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061613634","display_name":"Shixiang Gu","orcid":"https://orcid.org/0000-0001-9246-0896","observed_orcids":["https://orcid.org/0000-0001-9246-0896"]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Gu, Shixiang Shane","raw_affiliation_strings":["Google DeepMind","The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048764935","display_name":"\u0130zzeddin G\u00fcr","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gur, Izzeddin","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":119,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.7416999936103821,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.7416999936103821,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.10750000178813934,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.033799998462200165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-agents","display_name":"multimodal agents","score":0.7070000171661377},{"id":"https://openalex.org/keywords/instruction-tuning","display_name":"instruction tuning","score":0.6299999952316284},{"id":"https://openalex.org/keywords/vision-language-foundation-models","display_name":"vision-language foundation models","score":0.9710000157356262},{"id":"https://openalex.org/keywords/offline-training","display_name":"offline training","score":0.578000009059906},{"id":"https://openalex.org/keywords/demonstration-data","display_name":"demonstration data","score":0.33899998664855957},{"id":"https://openalex.org/keywords/time-perception","display_name":"time perception","score":0.5189999938011169},{"id":"https://openalex.org/keywords/multi-step-reasoning","display_name":"multi-step reasoning","score":0.7730000019073486},{"id":"https://openalex.org/keywords/webshop","display_name":"WebShop","score":0.8289999961853027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8960018157958984},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6716146469116211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5415154099464417},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49472948908805847},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.47558534145355225},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46110066771507263},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43645596504211426},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43059343099594116},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35642632842063904},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3429543972015381},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.11854","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.11854","pdf_url":"https://arxiv.org/pdf/2305.11854","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.2305.11854","doi":"https://doi.org/10.48550/arxiv.2305.11854","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.11854","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":"pmh:oai:arXiv.org:2305.11854","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.11854","pdf_url":"https://arxiv.org/pdf/2305.11854","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4377372292.pdf","grobid_xml":"https://content.openalex.org/works/W4377372292.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W2885185669","https://openalex.org/W2896457183","https://openalex.org/W2962843773","https://openalex.org/W2973727699","https://openalex.org/W2982399380","https://openalex.org/W2997154779","https://openalex.org/W3001279689","https://openalex.org/W3030163527","https://openalex.org/W3094356545","https://openalex.org/W3094502228","https://openalex.org/W3116323972","https://openalex.org/W3135367836","https://openalex.org/W3159481202","https://openalex.org/W3164797848","https://openalex.org/W3172942063","https://openalex.org/W3173325518","https://openalex.org/W3175937066","https://openalex.org/W3177813494","https://openalex.org/W3182696977","https://openalex.org/W3195140297","https://openalex.org/W3201589287","https://openalex.org/W3203833108","https://openalex.org/W3206072662","https://openalex.org/W3206324399","https://openalex.org/W4200630175","https://openalex.org/W4221152848","https://openalex.org/W4221167659","https://openalex.org/W4224442590","https://openalex.org/W4224912544","https://openalex.org/W4225323055","https://openalex.org/W4226002507","https://openalex.org/W4226227340","https://openalex.org/W4226278401","https://openalex.org/W4226279206","https://openalex.org/W4226352076","https://openalex.org/W4285428875","https://openalex.org/W4296406182","https://openalex.org/W4303648971","https://openalex.org/W4304192731","https://openalex.org/W4304195432","https://openalex.org/W4304697829","https://openalex.org/W4304699955","https://openalex.org/W4307079201","https://openalex.org/W4307868887","https://openalex.org/W4310286397","https://openalex.org/W4312205996","https://openalex.org/W4313679638","https://openalex.org/W4327810158","https://openalex.org/W4366330503","https://openalex.org/W4376312115","https://openalex.org/W4380715434","https://openalex.org/W4385262076","https://openalex.org/W4385430679","https://openalex.org/W4386065837","https://openalex.org/W4410536678","https://openalex.org/W7103485097","https://openalex.org/W7133187879","https://openalex.org/W7133210150","https://openalex.org/W7133215859","https://openalex.org/W7133218707","https://openalex.org/W7133224126","https://openalex.org/W7133225605","https://openalex.org/W7133227044","https://openalex.org/W7133261304"],"related_works":["https://openalex.org/W7202196605","https://openalex.org/W4404312229","https://openalex.org/W7127332544","https://openalex.org/W7006598167","https://openalex.org/W4401856679","https://openalex.org/W4391272423","https://openalex.org/W7116586765","https://openalex.org/W4390601403","https://openalex.org/W4412944906","https://openalex.org/W7213286829"],"abstract_inverted_index":{"The":[0],"progress":[1],"of":[2,14,99,110],"autonomous":[3],"web":[4,45,68],"navigation":[5,69],"has":[6],"been":[7],"hindered":[8],"by":[9,79,122,137],"the":[10,107,127,132,150,160,171,176],"dependence":[11],"on":[12,95,175],"billions":[13],"exploratory":[15],"interactions":[16],"via":[17],"online":[18],"reinforcement":[19],"learning,":[20],"and":[21,63,66,74,86,92,116,146,194],"domain-specific":[22],"model":[23,85,155],"designs":[24],"that":[25,58],"make":[26,195],"it":[27],"difficult":[28],"to":[29,159,170,198],"leverage":[30],"generalization":[31],"from":[32],"rich":[33],"out-of-domain":[34],"data.":[35],"In":[36],"this":[37,104,203],"work,":[38,193],"we":[39,129],"study":[40],"data-driven":[41],"offline":[42,135],"training":[43],"for":[44],"agents":[46],"with":[47,90],"vision-language":[48],"foundation":[49],"models.":[50],"We":[51,101,178],"propose":[52],"an":[53,82],"instruction-following":[54],"multimodal":[55,112],"agent,":[56],"WebGUM,":[57],"observes":[59],"both":[60],"webpage":[61],"screenshots":[62],"HTML":[64,114],"pages":[65],"outputs":[67],"actions,":[70],"such":[71],"as":[72],"click":[73],"type.":[75],"WebGUM":[76,165],"is":[77],"trained":[78,186],"jointly":[80],"finetuning":[81],"instruction-finetuned":[83],"language":[84],"a":[87,96,123],"vision":[88],"encoder":[89],"temporal":[91],"local":[93],"perception":[94],"large":[97],"corpus":[98],"demonstrations.":[100],"empirically":[102],"demonstrate":[103],"recipe":[105],"improves":[106],"agent's":[108],"ability":[109],"grounded":[111],"perception,":[113],"comprehension,":[115],"multi-step":[117],"reasoning,":[118],"outperforming":[119,142],"prior":[120,192],"works":[121],"significant":[124],"margin.":[125],"On":[126,149],"MiniWoB,":[128],"improve":[130],"over":[131],"previous":[133],"best":[134],"methods":[136],"more":[138],"than":[139,191],"45.8%,":[140],"even":[141],"online-finetuned":[143],"SoTA,":[144,162],"humans,":[145],"GPT-4-based":[147],"agent.":[148],"WebShop":[151],"benchmark,":[152],"our":[153,185],"3-billion-parameter":[154],"achieves":[156],"superior":[157],"performance":[158],"existing":[161],"PaLM-540B.":[163],"Furthermore,":[164],"exhibits":[166],"strong":[167],"positive":[168],"transfer":[169],"real-world":[172],"planning":[173],"tasks":[174],"Mind2Web.":[177],"also":[179],"collect":[180],"347K":[181],"high-quality":[182],"demonstrations":[183],"using":[184],"models,":[187],"38":[188],"times":[189],"larger":[190],"them":[196],"available":[197],"promote":[199],"future":[200],"research":[201],"in":[202],"direction.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":25},{"year":2025,"cited_by_count":47},{"year":2024,"cited_by_count":41},{"year":2023,"cited_by_count":6}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-05-23T00:00:00"}