{"id":"https://openalex.org/W4412945695","doi":"https://doi.org/10.18653/v1/2025.acl-long.277","title":"OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis","display_name":"OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945695","doi":"https://doi.org/10.18653/v1/2025.acl-long.277"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.277","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102007400","display_name":"Qiushi Sun","orcid":"https://orcid.org/0000-0002-5207-818X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiushi Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001863177","display_name":"Kanzhi Cheng","orcid":"https://orcid.org/0009-0004-4532-1446"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kanzhi Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093925435","display_name":"Zichen Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zichen Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111334406","display_name":"Chuanyang Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuanyang Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115589383","display_name":"Yian Wang","orcid":"https://orcid.org/0009-0002-9268-0527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yian Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111315441","display_name":"Fangzhi Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fangzhi Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065546087","display_name":"Zhenyu Wu","orcid":"https://orcid.org/0000-0002-0025-3521"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenyu Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062654071","display_name":"Chengyou Jia","orcid":"https://orcid.org/0000-0001-6921-0303"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengyou Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082276228","display_name":"L. Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liheng Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049003506","display_name":"Zhoumianze Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhoumianze Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063695659","display_name":"Ben Kao","orcid":"https://orcid.org/0000-0002-0501-9435"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Kao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100759678","display_name":"Guohao Li","orcid":"https://orcid.org/0000-0003-0260-5129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guohao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015879697","display_name":"Junxian He","orcid":"https://orcid.org/0009-0007-9559-6941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junxian He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102922010","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0003-4045-8473"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100955324","display_name":"Zhiyong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5555","last_page":"5579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9603999853134155,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9603999853134155,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9311000108718872,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9289000034332275,"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":0.7407934665679932},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6744570136070251},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5942693948745728},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3909105956554413},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3806759715080261},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37144899368286133},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.36625832319259644},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3285902440547943},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1534552276134491},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.11203283071517944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7407934665679932},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6744570136070251},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5942693948745728},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3909105956554413},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3806759715080261},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37144899368286133},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.36625832319259644},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3285902440547943},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1534552276134491},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.11203283071517944},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.277","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:hub.hku.hk:10722/359291","is_oa":false,"landing_page_url":"https://hub.hku.hk/handle/10722/359291","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Conference_Paper"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-167257","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-167257","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4323768008","https://openalex.org/W1941703695","https://openalex.org/W3131574667","https://openalex.org/W4360995134","https://openalex.org/W4248382324","https://openalex.org/W3023605104","https://openalex.org/W2039473718","https://openalex.org/W2387529410","https://openalex.org/W2383578611","https://openalex.org/W2987583674"],"abstract_inverted_index":{"Graphical":[0],"User":[1],"Interface":[2],"(GUI)":[3],"agents":[4,106,144],"powered":[5],"by":[6],"Vision-Language":[7],"Models":[8],"(VLMs)":[9],"have":[10],"demonstrated":[11],"human-like":[12],"computer":[13],"control":[14],"capability.":[15],"Despite":[16],"their":[17,149],"utility":[18],"in":[19],"advancing":[20],"digital":[21],"automation,":[22],"a":[23,85],"critical":[24],"bottleneck":[25],"persists:":[26],"collecting":[27,36],"high-quality":[28,118],"trajectory":[29,95,125],"data":[30,38,45,59,67,74,88,165],"for":[31,35],"training.":[32],"Common":[33],"practices":[34],"such":[37],"rely":[39],"on":[40,101,151],"human":[41],"supervision":[42],"or":[43,55],"synthetic":[44,73],"generation":[46],"through":[47],"executing":[48],"pre-defined":[49,102],"tasks,":[50,103],"which":[51],"are":[52,179],"either":[53],"resource-intensive":[54],"unable":[56],"to":[57,108,120,131,170],"guarantee":[58],"quality.":[60],"Moreover,":[61],"these":[62,80],"methods":[63],"suffer":[64],"from":[65],"limited":[66],"diversity":[68,168],"and":[69,75,111,162,167,177],"significant":[70],"gaps":[71],"between":[72],"real-world":[76],"environments.":[77],"To":[78],"address":[79],"challenges,":[81],"we":[82],"propose":[83],"OS-Genesis,":[84],"novel":[86],"GUI":[87,143],"synthesis":[89,172],"pipeline":[90],"that":[91,141],"reverses":[92],"the":[93,133,136],"conventional":[94],"collection":[96],"process.":[97],"Instead":[98],"of":[99,135],"relying":[100],"OS-Genesis":[104,146,182],"enables":[105],"first":[107],"perceive":[109],"environments":[110],"perform":[112],"step-wise":[113],"interactions,":[114],"then":[115,129],"retrospectively":[116],"derive":[117],"tasks":[119],"enable":[121],"trajectory-level":[122],"exploration.":[123],"A":[124],"reward":[126],"model":[127],"is":[128],"employed":[130],"ensure":[132],"quality":[134,166],"generated":[137],"trajectories.":[138],"We":[139],"demonstrate":[140],"training":[142],"with":[145],"significantly":[147],"improves":[148],"performance":[150],"highly":[152],"challenging":[153],"online":[154],"benchmarks.":[155],"In-depth":[156],"analysis":[157],"further":[158],"validates":[159],"OS-Genesis's":[160],"efficiency":[161],"its":[163],"superior":[164],"compared":[169],"existing":[171],"methods.":[173],"Our":[174],"codes,":[175],"data,":[176],"checkpoints":[178],"available":[180],"at":[181],"Homepage.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
