{"id":"https://openalex.org/W4415708166","doi":"https://doi.org/10.1109/icme59968.2025.11209200","title":"G-TADS: GUI Task-Ability Decoupling Strategy for High-Adaptability Multimodal Intelligent Agents","display_name":"G-TADS: GUI Task-Ability Decoupling Strategy for High-Adaptability Multimodal Intelligent Agents","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708166","doi":"https://doi.org/10.1109/icme59968.2025.11209200"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5045366440","display_name":"Zhiqiang Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiqiang Xia","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019122904","display_name":"Xinyuan Zhang","orcid":"https://orcid.org/0000-0002-2002-8110"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyuan Zhang","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018588825","display_name":"Yang Li","orcid":"https://orcid.org/0000-0002-4268-4004"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373054","display_name":"Yuchen Liu","orcid":"https://orcid.org/0000-0002-6517-0022"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Liu","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107079867","display_name":"Runyu Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runyu Shi","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101746187","display_name":"Jiaming Xu","orcid":"https://orcid.org/0000-0001-7635-1059"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Xu","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5045366440"],"corresponding_institution_ids":["https://openalex.org/I862669128"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33756663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5615000128746033,"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":0.5615000128746033,"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":0.11029999703168869,"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/T12031","display_name":"Speech and dialogue systems","score":0.07190000265836716,"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/automation","display_name":"Automation","score":0.629800021648407},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.6265000104904175},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5931000113487244},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5098000168800354},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.45590001344680786},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.4544000029563904},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.424699991941452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752000093460083},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.629800021648407},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.6265000104904175},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5931000113487244},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.520799994468689},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5098000168800354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47760000824928284},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.45590001344680786},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3709999918937683},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35659998655319214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C66153210","wikidata":"https://www.wikidata.org/wiki/Q5597182","display_name":"Graphical user interface testing","level":4,"score":0.2854999899864197},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C56397880","wikidata":"https://www.wikidata.org/wiki/Q6044094","display_name":"Intelligent decision support system","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C137703981","wikidata":"https://www.wikidata.org/wiki/Q4692093","display_name":"Agent architecture","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W4402670435","https://openalex.org/W4402671607","https://openalex.org/W4402713111","https://openalex.org/W4402753874","https://openalex.org/W4404792858","https://openalex.org/W4413147863"],"related_works":[],"abstract_inverted_index":{"Graphical":[0],"User":[1],"Interface":[2],"(GUI)":[3],"automation":[4],"aims":[5],"to":[6],"help":[7],"users":[8],"interact":[9],"with":[10,23,135],"devices":[11],"efficiently,":[12],"and":[13,52,73,115,128],"the":[14,47,81,92,121,125,129],"integration":[15],"of":[16,49],"open-source":[17,34],"multimodal":[18,100],"large":[19],"language":[20],"models":[21],"(MLLMs)":[22],"GUI":[24,39,99],"agents":[25],"shows":[26],"great":[27],"potential":[28],"in":[29,57,60,143],"this":[30,67],"area.":[31],"However,":[32],"existing":[33],"model-based":[35],"solutions":[36],"typically":[37],"treat":[38],"tasks":[40,106],"as":[41],"a":[42,98],"single":[43],"end-to-end":[44],"process,":[45],"overlooking":[46],"optimization":[48],"input-output":[50,71],"design":[51],"training":[53],"strategies,":[54],"which":[55,132],"results":[56],"poor":[58],"performance":[59],"real-world":[61],"applications.":[62],"To":[63],"address":[64],"these":[65],"issues,":[66],"paper":[68],"systematically":[69],"analyzes":[70],"strategies":[72],"finds":[74],"that":[75,104],"incorporating":[76],"historical":[77],"operation":[78,112],"descriptions":[79,114],"into":[80,107],"input":[82],"significantly":[83],"enhances":[84],"task":[85],"performance.":[86],"Based":[87],"on":[88,124],"this,":[89],"we":[90,133],"propose":[91],"Task":[93],"Ability":[94],"Decoupling":[95],"Strategy":[96],"(G-TADS),":[97],"intelligent":[101],"agent":[102],"framework":[103,123],"decomposes":[105],"two":[108],"independent":[109],"subtasks:":[110],"generating":[111,116],"semantic":[113,136],"specific":[117],"actions.":[118],"We":[119],"validated":[120],"G-TADS":[122],"AITZ":[126],"dataset":[127],"Mind2Web":[130],"dataset,":[131],"extended":[134],"annotations,":[137],"demonstrating":[138],"its":[139],"strong":[140],"generalization":[141],"ability":[142],"multi-task":[144],"scenarios.":[145],"Our":[146],"code":[147],"is":[148],"available":[149],"at":[150],"https://github.com/xzq11111/G-TADS.":[151]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}