{"id":"https://openalex.org/W4412888940","doi":"https://doi.org/10.18653/v1/2025.findings-acl.76","title":"Ponder & Press: Advancing Visual GUI Agent towards General Computer Control","display_name":"Ponder & Press: Advancing Visual GUI Agent towards General Computer Control","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888940","doi":"https://doi.org/10.18653/v1/2025.findings-acl.76"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.76","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.76","pdf_url":"https://aclanthology.org/2025.findings-acl.76.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.76.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100662110","display_name":"Yiqin Wang","orcid":"https://orcid.org/0000-0003-4714-774X"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqin Wang","raw_affiliation_strings":["Shenzhen International Graduate School , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School , Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112582535","display_name":"Haoji Zhang","orcid":"https://orcid.org/0009-0000-1467-1719"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoji Zhang","raw_affiliation_strings":["Shenzhen International Graduate School , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School , Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102117540","display_name":"Jingqi Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqi Tian","raw_affiliation_strings":["Shenzhen International Graduate School , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School , Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101926295","display_name":"Yansong Tang","orcid":"https://orcid.org/0000-0002-8768-8498"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yansong Tang","raw_affiliation_strings":["Shenzhen International Graduate School , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School , Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1461","last_page":"1473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.508400022983551,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.508400022983551,"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/T10888","display_name":"Augmented Reality Applications","score":0.4729999899864197,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6845884323120117},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5734857320785522},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5363131165504456},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.34969842433929443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2660718560218811},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12080702185630798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6845884323120117},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5734857320785522},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5363131165504456},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.34969842433929443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2660718560218811},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12080702185630798}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.76","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.76","pdf_url":"https://aclanthology.org/2025.findings-acl.76.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.76","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.76","pdf_url":"https://aclanthology.org/2025.findings-acl.76.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888940.pdf","grobid_xml":"https://content.openalex.org/works/W4412888940.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Most":[0],"existing":[1,136],"GUI":[2,43,50,61,110,143,153,178],"agents":[3],"typically":[4],"depend":[5],"on":[6,140],"non-vision":[7],"inputs":[8],"like":[9],"HTML":[10],"source":[11],"code":[12],"or":[13],"accessibility":[14],"trees,":[15],"limiting":[16],"flexibility":[17],"across":[18,151],"diverse":[19],"software":[20],"environments":[21,154],"and":[22,60,147,160],"platforms.Current":[23],"multimodal":[24],"large":[25],"language":[26],"models":[27,137],"(MLLMs),":[28],"though":[29],"excel":[30],"at":[31],"using":[32],"vision":[33],"to":[34,53,129],"ground":[35],"real-world":[36,58],"objects,":[37],"often":[38],"struggle":[39],"with":[40,100],"accurately":[41],"localizing":[42],"elements":[44,111],"-a":[45],"critical":[46],"requirement":[47],"for":[48,73,91,112],"effective":[49],"automation":[51],"-due":[52],"the":[54,141,165,174],"semantic":[55],"gap":[56],"between":[57],"objects":[59],"elements.In":[62],"this":[63],"work,":[64],"we":[65],"introduce":[66],"Ponder":[67,166],"&":[68,132,167],"Press,":[69],"a":[70,84,101,105,116,123],"divide-and-conquer":[71],"framework":[72,169],"general":[74],"computer":[75],"control":[76],"that":[77,107,164],"uses":[78],"only":[79],"visual":[80,118,177],"input.Our":[81],"approach":[82],"combines":[83],"general-purpose":[85],"MLLM":[86,103],"as":[87,104],"an":[88],"'interpreter',":[89],"responsible":[90],"translating":[92],"high-level":[93],"user":[94],"instructions":[95],"into":[96],"detailed":[97],"action":[98,113],"descriptions,":[99],"GUI-specific":[102],"'locator'":[106],"precisely":[108],"locates":[109],"placement.By":[114],"leveraging":[115],"purely":[117],"input,":[119],"our":[120],"agent":[121,149],"offers":[122],"versatile,":[124],"human-like":[125],"interaction":[126],"paradigm":[127],"applicable":[128],"various":[130,152],"applications.Ponder":[131],"Press":[133,168],"locator":[134],"outperforms":[135],"by":[138],"+22.5%":[139],"ScreenSpot":[142],"grounding":[144],"benchmark.More":[145],"offline":[146],"interactive":[148],"benchmarks":[150],"-including":[155],"web":[156],"pages,":[157],"desktop":[158],"software,":[159],"mobile":[161],"UIs":[162],"-demonstrate":[163],"achieves":[170],"state-of-the-art":[171],"performance,":[172],"highlighting":[173],"potential":[175],"of":[176],"agents.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}