{"id":"https://openalex.org/W7214958795","doi":"https://doi.org/10.48550/arxiv.2609.34113","title":"GUITAR: Structured Failure Diagnosis of GUI Agents via State Transitions","display_name":"GUITAR: Structured Failure Diagnosis of GUI Agents via State Transitions","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214958795","doi":"https://doi.org/10.48550/arxiv.2609.34113"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.34113","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34113","pdf_url":"https://arxiv.org/pdf/2609.34113","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/2609.34113","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146893137","display_name":"Shaoqing Zhang","orcid":"https://orcid.org/0000-0001-6569-9842","observed_orcids":["https://orcid.org/0000-0001-6569-9842"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Shaoqing","raw_affiliation_strings":["Harbin Institute of Technology , Shenzhen , China","Pengcheng Laboratory , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology , Shenzhen , China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Pengcheng Laboratory , Shenzhen , China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153581373","display_name":"Kehai Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Kehai","raw_affiliation_strings":["Harbin Institute of Technology , Shenzhen , China","Pengcheng Laboratory , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology , Shenzhen , China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Pengcheng Laboratory , Shenzhen , China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153557649","display_name":"Xuefeng Bai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bai, Xuefeng","raw_affiliation_strings":["Harbin Institute of Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology , Shenzhen , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153650669","display_name":"Zhuosheng Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Zhuosheng","raw_affiliation_strings":["Shanghai Jiao Tong University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University , China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153607927","display_name":"Pengfei Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Pengfei","raw_affiliation_strings":["Pengcheng Laboratory , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory , Shenzhen , China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153582295","display_name":"Yang Xiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang, Yang","raw_affiliation_strings":["Pengcheng Laboratory , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory , Shenzhen , China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153665374","display_name":"Min Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Min","raw_affiliation_strings":["Harbin Institute of Technology , Shenzhen , China","Pengcheng Laboratory , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology , Shenzhen , China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Pengcheng Laboratory , Shenzhen , China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.8119999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.8119999766349792,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.02889999933540821,"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/T13287","display_name":"Robotic Process Automation Applications","score":0.02459999918937683,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gui-agents","display_name":"GUI agents","score":0.8240000009536743},{"id":"https://openalex.org/keywords/fault-diagnosis","display_name":"fault diagnosis","score":0.8659999966621399},{"id":"https://openalex.org/keywords/state-transition-diagrams","display_name":"state diagrams","score":0.8370000123977661},{"id":"https://openalex.org/keywords/error-localization","display_name":"error localization","score":0.47999998927116394}],"concepts":[{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.6988999843597412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6862000226974487},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4794999957084656},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4147000014781952},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.39480000734329224},{"id":"https://openalex.org/C102379954","wikidata":"https://www.wikidata.org/wiki/Q2589940","display_name":"Call graph","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3671000003814697},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.35019999742507935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34209999442100525},{"id":"https://openalex.org/C66153210","wikidata":"https://www.wikidata.org/wiki/Q5597182","display_name":"Graphical user interface testing","level":4,"score":0.33500000834465027},{"id":"https://openalex.org/C95543465","wikidata":"https://www.wikidata.org/wiki/Q6607","display_name":"Guitar","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33000001311302185},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30649998784065247},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C2984927552","wikidata":"https://www.wikidata.org/wiki/Q845734","display_name":"Graphical display","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C2984968299","wikidata":"https://www.wikidata.org/wiki/Q1077784","display_name":"Software tool","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.34113","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34113","pdf_url":"https://arxiv.org/pdf/2609.34113","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.2609.34113","doi":"https://doi.org/10.48550/arxiv.2609.34113","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.34113","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:2609.34113","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34113","pdf_url":"https://arxiv.org/pdf/2609.34113","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214958795.pdf","grobid_xml":"https://content.openalex.org/works/W7214958795.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W4379539325","https://openalex.org/W4388685755","https://openalex.org/W4398836283","https://openalex.org/W4399657805","https://openalex.org/W4404343203","https://openalex.org/W4405095669","https://openalex.org/W4406755521","https://openalex.org/W4407794264","https://openalex.org/W4415539539","https://openalex.org/W4416246521","https://openalex.org/W4416780398","https://openalex.org/W6891822422","https://openalex.org/W7077152995","https://openalex.org/W7119703633","https://openalex.org/W7128622255","https://openalex.org/W7151361041","https://openalex.org/W7166818502"],"related_works":["https://openalex.org/W7161731315","https://openalex.org/W7222200977","https://openalex.org/W7151361041","https://openalex.org/W7169859875","https://openalex.org/W4414887453","https://openalex.org/W7152641625","https://openalex.org/W7167638042","https://openalex.org/W4416236285","https://openalex.org/W7212151190","https://openalex.org/W6967135602"],"abstract_inverted_index":{"Understanding":[0],"where":[1],"and":[2,31,61,97,117,122,149,171,181],"why":[3],"Graphical":[4],"User":[5],"Interface":[6],"(GUI)":[7],"agents":[8,116,157],"fail":[9],"is":[10,185],"essential":[11],"for":[12],"building":[13],"more":[14],"reliable":[15],"systems,":[16],"yet":[17],"current":[18],"evaluation":[19,161,176],"relies":[20],"on":[21,69],"step":[22],"accuracy,":[23],"a":[24,85,100,138,151],"metric":[25],"that":[26,89,126],"treats":[27],"each":[28],"screen":[29],"independently":[30],"overlooks":[32],"the":[33,63,169,178],"underlying":[34],"structure":[35],"of":[36,128,133,141,174],"GUI":[37,65],"environments.":[38],"This":[39],"leads":[40],"to":[41,110,137],"two":[42],"critical":[43,72],"blind":[44],"spots:":[45],"(1)":[46],"functionally":[47],"equivalent":[48],"screens":[49,73,109],"are":[50],"evaluated":[51,179],"in":[52,131],"isolation,":[53],"obscuring":[54],"systematic":[55],"failure":[56,92],"patterns":[57],"across":[58,155],"shared":[59,111],"screens;":[60],"(2)":[62],"long-tailed":[64],"distribution":[66],"renders":[67],"failures":[68,129],"rare":[70],"but":[71],"invisible":[74],"under":[75,158],"standard":[76],"metrics.":[77],"To":[78],"address":[79],"these":[80],"issues,":[81],"we":[82],"propose":[83],"\\textbf{GUITAR},":[84],"state-centric":[86],"diagnostic":[87,170],"framework":[88],"performs":[90],"structured":[91],"analysis":[93],"over":[94],"both":[95],"states":[96],"transitions,":[98],"using":[99],"State":[101],"Transition":[102],"Graph":[103],"(STG)":[104],"by":[105,147],"mapping":[106],"visually":[107],"diverse":[108],"functional":[112],"states.":[113],"Across":[114],"8":[115],"6":[118],"tasks":[119],"from":[120],"AndroidControl":[121],"Mind2Web,":[123],"GUITAR":[124],"reveals":[125],"60.4\\%":[127],"occur":[130],"20\\%":[132],"states,":[134],"localizing":[135],"errors":[136],"small":[139],"set":[140],"bottlenecks.":[142],"Bottleneck-targeted":[143],"guidance":[144],"improves":[145],"SR":[146],"2.8\\%":[148],"retains":[150],"1.88\\%":[152],"average":[153],"gain":[154],"7":[156],"three-fold":[159],"trajectory-held-out":[160],"with":[162],"fully":[163],"automatic":[164],"STGs.":[165],"These":[166],"findings":[167],"demonstrate":[168],"actionable":[172],"value":[173],"structure-aware":[175],"within":[177],"mobile":[180],"web":[182],"tasks.":[183],"Code":[184],"available":[186],"at":[187],"https://github.com/sqzhang-lazy/GUITAR":[188]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}
