{"id":"https://openalex.org/W4415329388","doi":"https://doi.org/10.52202/085713-3201","title":"GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents","display_name":"GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415329388","doi":"https://doi.org/10.52202/085713-3201"},"language":"en","primary_location":{"id":"doi:10.52202/085713-3201","doi":"https://doi.org/10.52202/085713-3201","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-3201","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.15810","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089264212","display_name":"Yuqi Zhou","orcid":"https://orcid.org/0000-0003-3415-9944","observed_orcids":["https://orcid.org/0000-0003-3415-9944"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Zhou","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075518954","display_name":"Sunhao Dai","orcid":"https://orcid.org/0009-0002-7549-0860","observed_orcids":["https://orcid.org/0009-0002-7549-0860"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sunhao Dai","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047862167","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-1381-9678","observed_orcids":["https://orcid.org/0000-0002-1381-9678","https://orcid.org/0000-0002-0288-4212","https://orcid.org/0000-0003-3730-6401"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101842986","display_name":"Kaiwen Zhou","orcid":"https://orcid.org/0009-0006-0779-5450","observed_orcids":["https://orcid.org/0009-0006-0779-5450"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kaiwen Zhou","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qinglin Jia","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinglin Jia","raw_affiliation_strings":["Huawei Technologies Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Jun Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xu","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7413,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.95804019,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"106088","last_page":"106110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1800999939441681,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1800999939441681,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.12790000438690186,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.0568000003695488,"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/visual-grounding","display_name":"visual grounding","score":0.9259999990463257},{"id":"https://openalex.org/keywords/chain-of-thought-reasoning","display_name":"chain-of-thought reasoning","score":0.8989999890327454},{"id":"https://openalex.org/keywords/online-reinforcement-learning","display_name":"online reinforcement learning","score":0.8349999785423279},{"id":"https://openalex.org/keywords/reward-hacking","display_name":"reward hacking","score":0.9580000042915344},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.6899999976158142},{"id":"https://openalex.org/keywords/length-normalization","display_name":"length normalization","score":0.6200000047683716},{"id":"https://openalex.org/keywords/object-localization","display_name":"object localization","score":0.47099998593330383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465000152587891},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6252999901771545},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6148999929428101},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5867999792098999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5338000059127808},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4871000051498413},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4075999855995178},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39340001344680786},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C180932941","wikidata":"https://www.wikidata.org/wiki/Q997233","display_name":"White box","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/085713-3201","doi":"https://doi.org/10.52202/085713-3201","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-3201","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.15810","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15810","pdf_url":"https://arxiv.org/pdf/2505.15810","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.15810","doi":"https://doi.org/10.48550/arxiv.2505.15810","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.15810","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.15810","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15810","pdf_url":"https://arxiv.org/pdf/2505.15810","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415329388.pdf","grobid_xml":"https://content.openalex.org/works/W4415329388.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417300636","https://openalex.org/W4416174529","https://openalex.org/W7163043814","https://openalex.org/W7131287138","https://openalex.org/W7128354292","https://openalex.org/W6948353082","https://openalex.org/W7083683689","https://openalex.org/W7221871878","https://openalex.org/W7137802127","https://openalex.org/W7131667860"],"abstract_inverted_index":{"Recent":[0],"Graphical":[1],"User":[2],"Interface":[3],"(GUI)":[4],"agents":[5],"replicate":[6],"the":[7,73,170,180,228],"R1-Zero":[8],"paradigm,":[9],"coupling":[10],"online":[11],"Reinforcement":[12],"Learning":[13],"(RL)":[14],"with":[15,206],"explicit":[16],"chain-of-thought":[17,77],"reasoning":[18,159],"prior":[19,220],"to":[20,64,75,84,101,106,118,123,131,173],"object":[21],"grounding":[22,66,86],"and":[23,50,109,127,187,213,225],"thereby":[24],"achieving":[25],"substantial":[26],"performance":[27],"gains.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,140,146,163,178],"first":[33],"conduct":[34],"extensive":[35],"analysis":[36],"experiments":[37],"of":[38,42,222],"three":[39,142],"key":[40],"components":[41],"that":[43,152],"training":[44],"pipeline:":[45],"input":[46],"design,":[47],"output":[48],"evaluation,":[49],"policy":[51],"update-each":[52],"revealing":[53],"distinct":[54],"challenges":[55],"arising":[56],"from":[57],"blindly":[58],"applying":[59],"general-purpose":[60],"RL":[61,116,181],"without":[62],"adapting":[63],"GUI":[65,236],"tasks.":[67],"Input":[68],"design:":[69],"Current":[70],"templates":[71],"encourage":[72],"model":[74],"generate":[76],"reasoning,":[78],"but":[79],"longer":[80],"chains":[81],"unexpectedly":[82],"lead":[83],"worse":[85],"performance.":[87],"Output":[88],"evaluation:":[89],"Reward":[90],"functions":[91],"based":[92],"on":[93,133,196,202,211,215],"hit":[94],"signals":[95],"or":[96],"box":[97,103,166],"area":[98],"allow":[99],"models":[100,221],"exploit":[102],"size,":[104],"leading":[105,130],"reward":[107,171,175],"hacking":[108],"poor":[110],"localization":[111],"quality.":[112],"Policy":[113],"update:":[114],"Online":[115],"tends":[117],"overfit":[119],"easy":[120],"examples":[121],"due":[122],"biases":[124],"in":[125,235],"length":[126,185],"sample":[128],"difficulty,":[129],"under-optimization":[132],"harder":[134],"cases.":[135],"To":[136],"address":[137],"these":[138],"issues,":[139],"propose":[141],"targeted":[143],"solutions.":[144],"First,":[145],"adopt":[147],"a":[148,165,189,232],"Fast":[149],"Thinking":[150],"Template":[151],"encourages":[153],"direct":[154],"answer":[155],"generation,":[156],"reducing":[157],"excessive":[158],"during":[160],"training.":[161],"Second,":[162],"incorporate":[164],"size":[167,224],"constraint":[168],"into":[169],"function":[172],"mitigate":[174],"hacking.":[176],"Third,":[177],"revise":[179],"objective":[182],"by":[183],"adjusting":[184],"normalization":[186],"adding":[188],"difficulty-aware":[190],"scaling":[191],"factor,":[192],"enabling":[193],"better":[194],"optimization":[195],"hard":[197],"samples.":[198],"Our":[199],"GUI-G1-3B,":[200],"trained":[201],"17K":[203],"public":[204],"samples":[205],"Qwen2.5-VL-3B-Instruct,":[207],"achieves":[208],"90.3%":[209],"accuracy":[210],"ScreenSpot":[212],"37.1%":[214],"ScreenSpot-Pro.":[216],"This":[217],"surpasses":[218],"all":[219],"similar":[223],"even":[226],"outperforms":[227],"larger":[229],"UI-TARS-7B,":[230],"establishing":[231],"new":[233],"state-of-the-art":[234],"agent":[237],"grounding.":[238],"The":[239],"project":[240],"repository":[241],"is":[242],"available":[243],"at":[244],"https://github.com/Yuqi-Zhou/GUI-G1.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-10-10T09:11:00.788812","created_date":"2025-10-19T00:00:00"}