{"id":"https://openalex.org/W7140742687","doi":"https://doi.org/10.48550/arxiv.2603.24533","title":"UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience","display_name":"UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7140742687","doi":"https://doi.org/10.48550/arxiv.2603.24533"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.24533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24533","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.24533","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130683550","display_name":"Zichuan Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lin, Zichuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085565104","display_name":"Feiyu Liu","orcid":"https://orcid.org/0000-0003-4309-1064"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Feiyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130703462","display_name":"Yijun Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yijun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130633249","display_name":"Jiafei Lyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Jiafei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130690827","display_name":"Yiming Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Yiming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130658134","display_name":"Yicheng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yicheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130665614","display_name":"Zhicong Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Zhicong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130651818","display_name":"Yangbin Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yangbin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130663813","display_name":"Mingyu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Mingyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125210509","display_name":"Junyou Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Junyou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130630716","display_name":"Deheng Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Deheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130631489","display_name":"Jie Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jie","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5130683550"],"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":0.10480000078678131,"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":0.10480000078678131,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.06669999659061432,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.06040000170469284,"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/automation","display_name":"Automation","score":0.5516999959945679},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.40470001101493835},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.34769999980926514},{"id":"https://openalex.org/keywords/mobile-apps","display_name":"Mobile apps","score":0.33980000019073486},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.314300000667572},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.28769999742507935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7874000072479248},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.5516999959945679},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5367000102996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44920000433921814},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C2988145974","wikidata":"https://www.wikidata.org/wiki/Q620615","display_name":"Mobile apps","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3034999966621399},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.24533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24533","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.24533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24533","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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"mobile":[1,50,148],"GUI":[2,38,51,149],"agents":[3],"have":[4],"attracted":[5],"increasing":[6],"attention":[7],"along":[8],"with":[9],"the":[10,54,64,133],"advancement":[11],"of":[12,67,135],"Multimodal":[13],"Large":[14],"Language":[15],"Models":[16],"(MLLMs).":[17],"However,":[18],"existing":[19],"methods":[20],"still":[21],"suffer":[22],"from":[23,26,97],"inefficient":[24],"learning":[25],"failed":[27,102],"trajectories":[28,99],"and":[29,69,92,123,128,146],"ambiguous":[30],"credit":[31],"assignment":[32],"under":[33],"sparse":[34],"rewards":[35],"for":[36],"long-horizon":[37],"tasks.":[39],"To":[40],"that":[41,109],"end,":[42],"we":[43,57],"propose":[44],"UI-Voyager,":[45],"a":[46,72,140],"novel":[47],"two-stage":[48],"self-evolving":[49],"agent.":[52],"In":[53],"first":[55],"stage,":[56],"employ":[58],"Rejection":[59],"Fine-Tuning":[60],"(RFT),":[61],"which":[62,84],"enables":[63],"continuous":[65],"co-evolution":[66],"data":[68,154],"models":[70],"in":[71,89],"fully":[73],"autonomous":[74],"loop.":[75],"The":[76],"second":[77],"stage":[78],"introduces":[79],"Group":[80],"Relative":[81],"Self-Distillation":[82],"(GRSD),":[83],"identifies":[85],"critical":[86],"fork":[87],"points":[88],"group":[90],"rollouts":[91],"constructs":[93],"dense":[94],"step-level":[95],"supervision":[96],"successful":[98],"to":[100],"correct":[101],"ones.":[103],"Extensive":[104],"experiments":[105],"on":[106],"AndroidWorld":[107],"show":[108],"our":[110],"4B":[111],"model":[112],"achieves":[113],"an":[114],"81.0%":[115],"Pass@1":[116],"success":[117],"rate,":[118],"outperforming":[119],"numerous":[120],"recent":[121],"baselines":[122],"exceeding":[124],"human-level":[125],"performance.":[126],"Ablation":[127],"case":[129],"studies":[130],"further":[131],"verify":[132],"effectiveness":[134],"GRSD.":[136],"Our":[137],"method":[138],"represents":[139],"significant":[141],"leap":[142],"toward":[143],"efficient,":[144],"self-evolving,":[145],"high-performance":[147],"automation":[150],"without":[151],"expensive":[152],"manual":[153],"annotation.":[155]},"counts_by_year":[],"updated_date":"2026-03-27T06:05:27.210665","created_date":"2026-03-27T00:00:00"}