{"id":"https://openalex.org/W7157540309","doi":"https://doi.org/10.48550/arxiv.2604.25380","title":"Benchmarking and Improving GUI Agents in High-Dynamic Environments","display_name":"Benchmarking and Improving GUI Agents in High-Dynamic Environments","publication_year":2026,"publication_date":"2026-04-28","ids":{"openalex":"https://openalex.org/W7157540309","doi":"https://doi.org/10.48550/arxiv.2604.25380"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.25380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25380","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.25380","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134837262","display_name":"Enqi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Enqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134822250","display_name":"Liyuan Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Liyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134855126","display_name":"Zhi Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Zhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134873888","display_name":"Yan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068807848","display_name":"Chenrui Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Chenrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134865328","display_name":"Yang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134826329","display_name":"Jingrong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jingrong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134827746","display_name":"Qing Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Qing","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/T10709","display_name":"Social Robot Interaction and HRI","score":0.24979999661445618,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.24979999661445618,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.19140000641345978,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.13199999928474426,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6953999996185303},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.6445000171661377},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.616100013256073},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5734000205993652},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5728999972343445},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5719000101089478},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4986000061035156},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.47850000858306885},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4706999957561493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800599992275238},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6953999996185303},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.6445000171661377},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.616100013256073},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5734000205993652},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5728999972343445},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5468999743461609},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5051000118255615},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49160000681877136},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.46000000834465027},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4422999918460846},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4390000104904175},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.25380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25380","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.25380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25380","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":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6700450778007507,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,220],"Graphical":[3],"User":[4],"Interface":[5],"(GUI)":[6],"agents":[7,33],"have":[8],"predominantly":[9],"focused":[10],"on":[11,36,194,211,228],"training":[12],"paradigms":[13],"like":[14],"supervised":[15],"fine-tuning":[16],"(SFT)":[17],"and":[18,86,117,128,146,164,170,191,204],"reinforcement":[19],"learning":[20],"(RL).":[21],"However,":[22],"the":[23,57,112,132,138,144,149,154,167,171,175,177,195,199,218],"challenge":[24],"of":[25,111,119,137,174],"high-dynamic":[26],"GUI":[27,59,81,139,222],"environments":[28],"remains":[29],"largely":[30],"underexplored.":[31],"Existing":[32],"typically":[34],"rely":[35],"a":[37,47,78,122,125,129],"single":[38],"screenshot":[39],"after":[40],"each":[41],"action":[42],"for":[43,64,104,143,207],"decision-making,":[44],"leading":[45],"to":[46,184,187],"partially":[48],"observable":[49],"(or":[50],"even":[51],"unobservable)":[52],"Markov":[53],"decision":[54],"process,":[55],"where":[56],"key":[58],"state":[60],"including":[61],"important":[62,92],"information":[63],"actions":[65],"is":[66],"often":[67],"inadequately":[68],"captured.":[69],"To":[70],"systematically":[71],"explore":[72],"this":[73],"challenge,":[74],"we":[75,98],"introduce":[76],"DynamicGUIBench,":[77],"comprehensive":[79],"online":[80],"benchmark":[82],"spanning":[83],"ten":[84],"applications":[85],"diverse":[87],"interaction":[88,113],"scenarios":[89],"characterized":[90],"by":[91],"interface":[93],"changes":[94],"between":[95,166],"actions.":[96,209],"Furthermore,":[97],"present":[99],"DynamicUI,":[100],"an":[101,181],"agent":[102,197],"designed":[103],"dynamic":[105,123,133,156,221],"interfaces,":[106],"which":[107],"takes":[108],"screen-recording":[109],"videos":[110],"process":[114],"as":[115,153],"input":[116],"consists":[118],"three":[120],"components:":[121],"perceiver,":[124],"refinement":[126,178],"strategy,":[127],"reflection.":[130],"Specifically,":[131],"perceiver":[134],"clusters":[135],"frames":[136,152,169],"video,":[140],"generates":[141],"captions":[142],"centroids,":[145],"iteratively":[147],"selects":[148],"most":[150],"informative":[151],"salient":[155],"context.":[157],"Considering":[158],"that":[159,214],"there":[160],"may":[161],"be":[162],"inconsistencies":[163],"noise":[165],"selected":[168],"textual":[172],"context":[173],"agent,":[176],"strategy":[179],"employs":[180],"action-conditioned":[182],"filtering":[183],"refine":[185],"thoughts":[186],"mitigate":[188],"thought-action":[189],"inconsistency":[190],"redundancy.":[192],"Based":[193],"refined":[196],"trajectories,":[198],"reflection":[200],"module":[201],"provides":[202],"effective":[203],"accurate":[205],"guidance":[206],"further":[208],"Experiments":[210],"DynamicGUIBench":[212],"demonstrate":[213],"DynamicUI":[215],"significantly":[216],"improves":[217],"performance":[219,227],"environments,":[223],"while":[224],"maintaining":[225],"competitive":[226],"other":[229],"public":[230],"benchmarks.":[231]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-30T00:00:00"}