{"id":"https://openalex.org/W7216339999","doi":"https://doi.org/10.48550/arxiv.2610.01215","title":"AutoGUIWorld: Image Generators as Visual World Models for GUI Agent","display_name":"AutoGUIWorld: Image Generators as Visual World Models for GUI Agent","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7216339999","doi":"https://doi.org/10.48550/arxiv.2610.01215"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.01215","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01215","pdf_url":"https://arxiv.org/pdf/2610.01215","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.01215","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5155828784","display_name":"Cheng Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155169336","display_name":"Yifan Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5156246684","display_name":"Yutao Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yutao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129046434","display_name":"Zhaohua Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhaohua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155563090","display_name":"Beiduo Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Beiduo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076832872","display_name":"Muxi Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Muxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5156010126","display_name":"Chenchen Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Chenchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043368238","display_name":"Hexuan Deng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Hexuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155148050","display_name":"Haolin Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Haolin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125473299","display_name":"Geyuan Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Geyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130644750","display_name":"Sa Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Sa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079632234","display_name":"Jianhuan Zhuo","orcid":"https://orcid.org/0000-0002-0449-6459","observed_orcids":["https://orcid.org/0000-0002-0449-6459"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo, Jianhuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128973600","display_name":"Qiuyong Xiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Qiuyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125021210","display_name":"Jianhao Ruan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruan, Jianhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155819678","display_name":"Yiran Peng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Yiran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155402728","display_name":"Jiayi Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiayi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5154449404","display_name":"Tian Ye","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5156026008","display_name":"Xinlei Yu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Xinlei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129069493","display_name":"Tianwen Jiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Tianwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155022537","display_name":"Jihong Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jihong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100614732","display_name":"Yuyu Luo","orcid":"https://orcid.org/0000-0001-9530-3327","observed_orcids":["https://orcid.org/0000-0001-9530-3327"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yuyu","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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.3125,"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"}},"topics":[{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.3125,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.1039000004529953,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T13287","display_name":"Robotic Process Automation Applications","score":0.046300001442432404,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gui-agents","display_name":"GUI agents","score":0.9660000205039978},{"id":"https://openalex.org/keywords/image-generators","display_name":"image generators","score":0.8159999847412109},{"id":"https://openalex.org/keywords/data-generation","display_name":"data generation","score":0.4659999907016754},{"id":"https://openalex.org/keywords/visual-priors","display_name":"visual priors","score":0.38999998569488525},{"id":"https://openalex.org/keywords/task-planning","display_name":"task planning","score":0.4259999990463257},{"id":"https://openalex.org/keywords/qwen3-5","display_name":"Qwen3.5","score":0.6430000066757202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900000214576721},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6629999876022339},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6486999988555908},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6029000282287598},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5853999853134155},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5356000065803528},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.5259000062942505},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45419999957084656},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.4334999918937683},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41040000319480896},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.37470000982284546},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35740000009536743},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3303999900817871},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3131999969482422},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C76518257","wikidata":"https://www.wikidata.org/wiki/Q271680","display_name":"Software framework","level":5,"score":0.257099986076355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.01215","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01215","pdf_url":"https://arxiv.org/pdf/2610.01215","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.2610.01215","doi":"https://doi.org/10.48550/arxiv.2610.01215","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.01215","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:2610.01215","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01215","pdf_url":"https://arxiv.org/pdf/2610.01215","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7213422143","https://openalex.org/W7220657830","https://openalex.org/W4415037683","https://openalex.org/W4412945695","https://openalex.org/W4416053443","https://openalex.org/W4405355468","https://openalex.org/W7166850759","https://openalex.org/W7128606687","https://openalex.org/W7161307843","https://openalex.org/W6966634743"],"abstract_inverted_index":{"GUI":[0,84,98],"agents":[1],"require":[2],"high-quality":[3],"interaction":[4,85],"trajectories":[5,25,86,165,193],"to":[6,12,82,138,175,186],"learn":[7],"how":[8],"software":[9,93],"environments":[10],"respond":[11],"actions,":[13],"maintain":[14],"state,":[15,110],"and":[16,33,47,57,108,111,124,144,159,177,200],"support":[17],"multi-step":[18],"workflows.":[19],"However,":[20],"the":[21,29,37,69,76,91,135,167,178],"diversity":[22],"of":[23,72,79,103],"available":[24],"is":[26],"constrained":[27],"by":[28],"applications,":[30],"interface":[31,109],"states,":[32],"workflows":[34],"accessible":[35],"in":[36],"underlying":[38],"environments.":[39,94],"Expanding":[40],"this":[41],"coverage":[42],"requires":[43],"deploying":[44,88],"increasingly":[45],"diverse":[46],"complex":[48],"software,":[49],"with":[50,75],"specialized":[51],"applications":[52],"imposing":[53],"additional":[54],"installation,":[55],"configuration,":[56],"runtime":[58],"costs.":[59],"We":[60],"introduce":[61],"AutoGUIWorld,":[62],"a":[63,80],"data":[64],"generation":[65],"framework":[66],"that":[67,191],"combines":[68],"visual":[70,106,127],"priors":[71],"image":[73,131],"generators":[74],"task":[77,169,179],"knowledge":[78],"planner":[81,119],"synthesize":[83],"without":[87],"or":[89],"running":[90],"corresponding":[92],"AutoGUIWorld":[95,164],"samples":[96,154],"initial":[97],"scenes":[99],"from":[100,173,184],"structured":[101],"specifications":[102],"operating-system":[104],"context,":[105],"appearance,":[107],"generates":[112],"tasks":[113],"conditioned":[114],"on":[115,163,171,182,197],"those":[116],"scenes.":[117],"A":[118],"then":[120],"specifies":[121],"atomic":[122],"actions":[123],"their":[125],"intended":[126],"consequences,":[128],"while":[129],"an":[130],"generator":[132],"iteratively":[133],"edits":[134],"current":[136],"screenshot":[137],"produce":[139],"subsequent":[140],"observations.":[141],"Action":[142],"grounding":[143],"transition-level":[145],"quality":[146],"filtering":[147],"yield":[148],"79,266":[149],"spatially":[150],"annotated":[151],"step-level":[152],"training":[153],"across":[155],"Ubuntu,":[156],"Windows,":[157],"macOS,":[158],"Chrome.":[160],"Fine-tuning":[161],"Qwen3.5-35B-A3B":[162],"improves":[166],"mean":[168],"score":[170],"OSWorld":[172],"33.0%":[174],"40.8%":[176],"success":[180],"rate":[181],"ScienceBoard":[183],"14.0%":[185],"32.2%.":[187],"These":[188],"results":[189],"show":[190],"generated":[192],"improve":[194],"GUI-agent":[195],"performance":[196],"real":[198],"desktop":[199],"scientific":[201],"tasks.":[202]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-03T00:00:00"}
