{"id":"https://openalex.org/W7223137232","doi":"https://doi.org/10.48550/arxiv.2610.27977","title":"LiveUIBench: Evaluating Agent as App Workflows","display_name":"LiveUIBench: Evaluating Agent as App Workflows","publication_year":2026,"publication_date":"2026-10-20","ids":{"openalex":"https://openalex.org/W7223137232","doi":"https://doi.org/10.48550/arxiv.2610.27977"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.27977","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.27977","pdf_url":"https://arxiv.org/pdf/2610.27977","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.27977","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159182612","display_name":"Tong Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Tong","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5156275686","display_name":"Yuxuan Cheng","orcid":"https://orcid.org/0009-0000-4224-8838","observed_orcids":["https://orcid.org/0009-0000-4224-8838"]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng, Yuxuan","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159219914","display_name":"Ruimin Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Ruimin","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101845156","display_name":"Yun Peng","orcid":"https://orcid.org/0000-0003-1936-5598","observed_orcids":["https://orcid.org/0000-0003-1936-5598"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng, Yun","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048118068","display_name":"Tao Xie","orcid":"https://orcid.org/0000-0002-6731-216X","observed_orcids":["https://orcid.org/0000-0002-6731-216X","https://orcid.org/0009-0007-4887-5032","https://orcid.org/0000-0002-2129-8868"]},"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":"Xie, Tao","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10470","display_name":"Usability and User Interface Design","score":0.2915000021457672,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10470","display_name":"Usability and User Interface Design","score":0.2915000021457672,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12031","display_name":"Speech and dialogue systems","score":0.14650000631809235,"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/T13197","display_name":"Spreadsheets and End-User Computing","score":0.06920000165700912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/personalized-applications","display_name":"personalized applications","score":0.7129999995231628},{"id":"https://openalex.org/keywords/user-interface-generation","display_name":"user interface generation","score":0.5709999799728394},{"id":"https://openalex.org/keywords/requirements-evolution","display_name":"requirements evolution","score":0.5860000252723694},{"id":"https://openalex.org/keywords/natural-language-requirements","display_name":"natural language requirements","score":0.6930000185966492},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.746999979019165},{"id":"https://openalex.org/keywords/agent-evaluation","display_name":"agent evaluation","score":0.3490000069141388},{"id":"https://openalex.org/keywords/personal-services","display_name":"personal services","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8217999935150146},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.7710999846458435},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7188000082969666},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.6308000087738037},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5954999923706055},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5156000256538391},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46050000190734863},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3896999955177307},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38670000433921814},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C143267671","wikidata":"https://www.wikidata.org/wiki/Q7901856","display_name":"User requirements document","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C15569618","wikidata":"https://www.wikidata.org/wiki/Q3561421","display_name":"Liveness","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C4927394","wikidata":"https://www.wikidata.org/wiki/Q787631","display_name":"Business Process Execution Language","level":4,"score":0.2542000114917755},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.27977","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.27977","pdf_url":"https://arxiv.org/pdf/2610.27977","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.2610.27977","doi":"https://doi.org/10.48550/arxiv.2610.27977","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.27977","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:2610.27977","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.27977","pdf_url":"https://arxiv.org/pdf/2610.27977","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223137232.pdf","grobid_xml":"https://content.openalex.org/works/W7223137232.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W2059216172","https://openalex.org/W2093495548","https://openalex.org/W2115210820","https://openalex.org/W2123448890","https://openalex.org/W2141125339","https://openalex.org/W2532847336","https://openalex.org/W2610474269","https://openalex.org/W2972018816","https://openalex.org/W3177813494","https://openalex.org/W3213368902","https://openalex.org/W4221161476","https://openalex.org/W4304195432","https://openalex.org/W4385327683","https://openalex.org/W4385474529","https://openalex.org/W4385682136","https://openalex.org/W4387835442","https://openalex.org/W4388964563","https://openalex.org/W4389518608","https://openalex.org/W4396832280","https://openalex.org/W4399836817","https://openalex.org/W4401201100","https://openalex.org/W4402671485","https://openalex.org/W4402671629","https://openalex.org/W4403622204","https://openalex.org/W4404545406","https://openalex.org/W4404782768","https://openalex.org/W4409746394","https://openalex.org/W4409886285","https://openalex.org/W4411120254","https://openalex.org/W4415248976","https://openalex.org/W4415797693","https://openalex.org/W4417136556","https://openalex.org/W7133215859","https://openalex.org/W7133222210","https://openalex.org/W7133227044","https://openalex.org/W7133236450","https://openalex.org/W7133239970","https://openalex.org/W7160416041","https://openalex.org/W7163679042"],"related_works":["https://openalex.org/W7147272091","https://openalex.org/W7162457700","https://openalex.org/W7223278550","https://openalex.org/W7222962263","https://openalex.org/W7166803525","https://openalex.org/W7153163473","https://openalex.org/W7221199529","https://openalex.org/W7212029276","https://openalex.org/W7163995874","https://openalex.org/W2170743618"],"abstract_inverted_index":{"Applications":[0,159],"provide":[1],"convenient":[2],"features":[3],"for":[4,20,126],"users":[5,12,59],"to":[6,46,75,154],"complete":[7,155],"daily":[8],"tasks.":[9],"However,":[10],"different":[11,15],"may":[13,31],"have":[14],"or":[16,40],"even":[17],"conflicting":[18],"requirements":[19,26,62,129,138],"the":[21,25,28,47,90,105,110,114,150,167],"same":[22,29],"application,":[23],"while":[24,73,107,118,165],"of":[27],"user":[30,91],"change":[32],"over":[33],"time.":[34],"Personalizing":[35],"applications":[36],"produced":[37],"by":[38],"agent-to-app":[39],"UI-to-code":[41],"approaches":[42],"can":[43,160,175],"require":[44],"changes":[45],"generated":[48],"implementation.":[49],"We":[50,81,131],"propose":[51],"Agent":[52],"as":[53,128],"App,":[54],"a":[55,70,86,123,134],"task":[56,169],"in":[57,63],"which":[58,84],"express":[60],"their":[61],"natural":[64],"language":[65],"and":[66,95,103,116,139,171],"an":[67],"agent":[68,100],"creates":[69],"personalized":[71],"application":[72],"continuing":[74],"supply":[76],"its":[77],"behavior":[78],"during":[79],"use.":[80],"implement":[82],"LiveUIAgent,":[83],"generates":[85],"task-specific":[87],"orchestration":[88,115],"connecting":[89],"interface,":[92],"saved":[93],"information,":[94],"service":[96],"actions.":[97],"A":[98],"shared":[99],"runtime":[101,121],"renders":[102],"updates":[104],"interface":[106,117],"carrying":[108],"out":[109],"requested":[111],"operations.":[112],"Revising":[113],"reusing":[119],"that":[120,149],"provides":[122],"lightweight":[124],"basis":[125],"personalization":[127],"evolve.":[130],"introduce":[132],"LiveUIBench,":[133],"benchmark":[135],"with":[136,177],"diverse":[137],"ordered":[140],"interactions":[141],"across":[142],"personal":[143],"services.":[144],"The":[145],"empirical":[146],"findings":[147],"show":[148],"evaluated":[151],"models":[152],"struggle":[153],"these":[156],"workflows":[157],"reliably.":[158],"satisfy":[161],"many":[162],"local":[163],"checks":[164],"leaving":[166],"overall":[168],"unfinished,":[170],"greater":[172],"partial":[173],"coverage":[174],"coincide":[176],"fewer":[178],"completed":[179],"workflows.":[180]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-22T00:00:00"}
