{"id":"https://openalex.org/W4415540031","doi":"https://doi.org/10.1145/3746027.3755695","title":"MVISU-Bench: Benchmarking Mobile Agents for Real-World Tasks by Multi-App, Vague, Interactive, Single-App and Unethical Instructions","display_name":"MVISU-Bench: Benchmarking Mobile Agents for Real-World Tasks by Multi-App, Vague, Interactive, Single-App and Unethical Instructions","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540031","doi":"https://doi.org/10.1145/3746027.3755695"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020007780","display_name":"Zeyu Huang","orcid":"https://orcid.org/0009-0004-2578-0135"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zeyu Huang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-2578-0135","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103695611","display_name":"Juyuan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juyuan Wang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-8263-1861","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047814067","display_name":"Longfeng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longfeng Chen","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-0478-7684","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120132240","display_name":"Boyi Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyi Xiao","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-5010-9805","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044575343","display_name":"Leng Cai","orcid":"https://orcid.org/0000-0003-4259-2350"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leng Cai","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4259-2350","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101296394","display_name":"Zeng YaWen","orcid":"https://orcid.org/0000-0003-1908-1157"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yawen Zeng","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1908-1157","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114357209","display_name":"Jin Xu","orcid":"https://orcid.org/0009-0001-8735-3532"},"institutions":[{"id":"https://openalex.org/I4210165547","display_name":"Dezhou University","ror":"https://ror.org/05mnjs436","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165547"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Xu","raw_affiliation_strings":["South China University of Technology, Guanzhou, China and Pazhou Lab, Guanzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-8735-3532","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guanzhou, China and Pazhou Lab, Guanzhou, China","institution_ids":["https://openalex.org/I4210165547"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5020007780"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34551283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8797","last_page":"8805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12203","display_name":"Mobile Agent-Based Network Management","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12203","display_name":"Mobile Agent-Based Network Management","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9193000197410583,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9175999760627747,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7317000031471252},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.6208999752998352},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.4684000015258789},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46299999952316284},{"id":"https://openalex.org/keywords/mobile-computing","display_name":"Mobile computing","score":0.43959999084472656},{"id":"https://openalex.org/keywords/mobile-apps","display_name":"Mobile apps","score":0.4065999984741211},{"id":"https://openalex.org/keywords/mobile-technology","display_name":"Mobile technology","score":0.3546999990940094},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.3228999972343445}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7317000031471252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.711899995803833},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.6208999752998352},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5217000246047974},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C2988145974","wikidata":"https://www.wikidata.org/wiki/Q620615","display_name":"Mobile apps","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C60952562","wikidata":"https://www.wikidata.org/wiki/Q6887246","display_name":"Mobile technology","level":3,"score":0.3546999990940094},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3276999890804291},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2808000147342682},{"id":"https://openalex.org/C201025465","wikidata":"https://www.wikidata.org/wiki/Q11248500","display_name":"User experience design","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C3017568202","wikidata":"https://www.wikidata.org/wiki/Q2899888","display_name":"User needs","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2646999955177307},{"id":"https://openalex.org/C546215728","wikidata":"https://www.wikidata.org/wiki/Q39531","display_name":"Bluetooth","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2234319012","display_name":null,"funder_award_id":"62372187","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6687295176","display_name":null,"funder_award_id":"2022YFC3601005","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W4399121418","https://openalex.org/W4401856679","https://openalex.org/W4401863510","https://openalex.org/W4402753874","https://openalex.org/W4403333948","https://openalex.org/W4403333972","https://openalex.org/W4403791736","https://openalex.org/W4410636342","https://openalex.org/W4414760685"],"related_works":[],"abstract_inverted_index":{"Given":[0],"the":[1,32,40,126,155],"significant":[2],"advances":[3],"in":[4,10],"Large":[5],"Vision":[6],"Language":[7],"Models":[8],"(LVLMs)":[9],"reasoning":[11],"and":[12,35,42,62,99,115,140,144,151,161],"visual":[13],"understanding,":[14],"mobile":[15,80,104,159],"agents":[16,160],"are":[17,29],"rapidly":[18],"emerging":[19],"to":[20,37,96,110,125],"meet":[21],"users'":[22],"automation":[23],"needs.":[24],"However,":[25],"existing":[26,158],"evaluation":[27],"benchmarks":[28],"disconnected":[30],"from":[31],"real":[33],"world":[34],"fail":[36],"adequately":[38],"address":[39],"diverse":[41],"complex":[43],"requirements":[44],"of":[45,51,138],"users.":[46],"From":[47],"our":[48],"extensive":[49,149],"collection":[50],"user":[52,101,163],"questionnaire,":[53],"we":[54,68,83,153],"identified":[55],"five":[56],"tasks:":[57],"Multi-App,":[58],"Vague,":[59],"Interactive,":[60],"Single-App,":[61],"Unethical":[63],"Instructions.":[64],"Around":[65],"these":[66],"tasks,":[67],"present":[69],"MVISU-Bench,":[70],"a":[71,86,92],"bilingual":[72],"benchmark":[73],"that":[74,89],"includes":[75],"404":[76],"tasks":[77],"across":[78],"137":[79],"applications.":[81],"Furthermore,":[82],"propose":[84],"Aider,":[85],"plug-and-play":[87],"module":[88],"acts":[90],"as":[91],"dynamic":[93],"prompt":[94],"prompter":[95],"mitigate":[97],"risks":[98],"clarify":[100],"intent":[102],"for":[103,142],"agents.":[105],"Our":[106],"Aider":[107],"is":[108],"easy":[109],"integrate":[111],"into":[112],"several":[113],"frameworks":[114],"has":[116],"successfully":[117],"improved":[118],"overall":[119],"success":[120,135],"rates":[121],"by":[122],"19.55%":[123],"compared":[124],"current":[127],"state-of-the-art":[128],"(SOTA)":[129],"on":[130],"MVISU-Bench.":[131],"Specifically,":[132],"it":[133],"achieves":[134],"rate":[136],"improvements":[137],"53.52%":[139],"29.41%":[141],"unethical":[143],"interactive":[145],"instructions,":[146],"respectively.":[147],"Through":[148],"experiments":[150],"analysis,":[152],"highlight":[154],"gap":[156],"between":[157],"real-world":[162],"expectations.":[164]},"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-25T00:00:00"}
