{"id":"https://openalex.org/W7162647680","doi":"https://doi.org/10.48550/arxiv.2605.28629","title":"Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents","display_name":"Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162647680","doi":"https://doi.org/10.48550/arxiv.2605.28629"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.28629","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28629","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.2605.28629","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137264589","display_name":"Zheng Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009313267","display_name":"Pengzhou Cheng","orcid":"https://orcid.org/0000-0003-0945-8790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Pengzhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100585973","display_name":"Zongru Wu","orcid":"https://orcid.org/0000-0002-5387-7821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zongru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137211470","display_name":"Yuan Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137201551","display_name":"Tianjie Ju","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ju, Tianjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137219628","display_name":"Aston Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Aston","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137258977","display_name":"Gongshen Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Gongshen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137234149","display_name":"Zhuosheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhuosheng","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.38830000162124634,"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":0.38830000162124634,"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/T10028","display_name":"Topic Modeling","score":0.2467000037431717,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.049300000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6977999806404114},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6069999933242798},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.42570000886917114},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.36169999837875366},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.3416000008583069},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.3246999979019165},{"id":"https://openalex.org/keywords/semantic-heterogeneity","display_name":"Semantic heterogeneity","score":0.32339999079704285},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.30709999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7757999897003174},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6977999806404114},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6069999933242798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867999792098999},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5490999817848206},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3605000078678131},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3416000008583069},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C2778180026","wikidata":"https://www.wikidata.org/wiki/Q18378163","display_name":"Semantic heterogeneity","level":4,"score":0.32339999079704285},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2964000105857849},{"id":"https://openalex.org/C20555606","wikidata":"https://www.wikidata.org/wiki/Q868575","display_name":"Empowerment","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.28629","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28629","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.2605.28629","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28629","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,12,104,186,195,209],"multimodal":[3],"large":[4],"language":[5],"models":[6],"(MLLMs)":[7],"have":[8],"shown":[9],"exceptional":[10],"potential":[11],"enabling":[13],"mobile-using":[14,52,106,173],"agents":[15,24,53,56,61,73,127,145],"to":[16,27,35,39,54,75,132,147],"autonomously":[17],"execute":[18,28],"human":[19,58,82],"instructions.":[20,66],"However,":[21,67],"fully":[22],"automated":[23],"often":[25],"try":[26],"tasks":[29],"even":[30],"when":[31,60],"they":[32],"are":[33,222],"unable":[34],"resolve":[36],"them,":[37],"leading":[38],"the":[40,122,140,170,205],"problem":[41],"of":[42,111],"over-execution.":[43],"Previous":[44],"studies":[45],"solve":[46],"it":[47],"by":[48,153,207],"training":[49],"a":[50,92],"interactive":[51,72],"let":[55],"request":[57],"interaction":[59,103,114,123],"can":[62],"not":[63],"complete":[64],"user":[65],"we":[68,90],"find":[69],"that":[70,97],"these":[71],"tend":[74],"exhibit":[76],"over-soliciting":[77],"behavior,":[78],"relying":[79],"excessively":[80],"on":[81,169],"intervention.":[83],"To":[84],"mitigate":[85],"both":[86,134],"over-execution":[87],"and":[88,101,117,136,179],"over-soliciting,":[89],"propose":[91],"universal":[93],"confidence":[94,118,137,141,151],"integration":[95],"framework":[96,109],"enables":[98],"confidence-driven":[99],"proactive":[100],"robust":[102],"MLLM-based":[105],"agents.":[107],"The":[108,220],"consists":[110],"two":[112],"stages:":[113],"capability":[115,124],"empowerment":[116,125],"bias":[119,142],"correction.":[120],"In":[121,139,199],"stage,":[126,144],"learn":[128,146],"through":[129],"supervised":[130],"fine-tuning":[131],"output":[133,148],"actions":[135],"scores.":[138],"correction":[143],"more":[149],"accurate":[150],"scores":[152],"combining":[154],"semantic":[155],"similarity":[156],"retrieval":[157],"with":[158,189,213],"direct":[159],"preference":[160],"optimization.":[161],"Experimental":[162],"results":[163],"show":[164],"Mobile-Aptus":[165,181,203],"achieves":[166],"state-of-the-art":[167],"performance":[168],"four":[171],"popular":[172],"agent":[174],"benchmarks:":[175],"OS-Kairos,":[176],"AITZ,":[177],"Meta-GUI,":[178],"AndroidControl.":[180],"consistently":[182],"outperforms":[183],"all":[184],"baselines":[185],"offline":[187],"benchmarks,":[188],"an":[190],"average":[191],"improvement":[192],"over":[193],"17\\%":[194],"task":[196,210],"success":[197,211],"rate.":[198],"real-world":[200],"dynamic":[201],"experiments,":[202],"surpasses":[204],"baseline":[206],"26%":[208],"rate":[212],"only":[214],"0.64":[215],"intervention":[216],"steps":[217],"per":[218],"instruction.":[219],"codes":[221],"available":[223],"at":[224],"https://github.com/Wuzheng02/Mobile-Aptus.":[225]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-29T00:00:00"}