{"id":"https://openalex.org/W7129198172","doi":"https://doi.org/10.48550/arxiv.2602.13653","title":"Building Autonomous GUI Navigation via Agentic-Q Estimation and Step-Wise Policy Optimization","display_name":"Building Autonomous GUI Navigation via Agentic-Q Estimation and Step-Wise Policy Optimization","publication_year":2026,"publication_date":"2026-02-14","ids":{"openalex":"https://openalex.org/W7129198172","doi":"https://doi.org/10.48550/arxiv.2602.13653"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.13653","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126215215","display_name":"Yibo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Yibo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Huzhang, Guangda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huzhang, Guangda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051919826","display_name":"Yuwei Hu","orcid":"https://orcid.org/0000-0002-0413-5143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yuwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126233630","display_name":"Yu Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024572427","display_name":"Shiyin Lu","orcid":"https://orcid.org/0000-0001-6438-5999"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Shiyin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126260791","display_name":"Qing-Guo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Qing-Guo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126245434","display_name":"Zhao Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109469218","display_name":"Weihua Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Weihua","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126245653","display_name":"Kaifu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kaifu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126234644","display_name":"Lijun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Lijun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5126215215"],"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":0.42170000076293945,"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":0.42170000076293945,"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/T12031","display_name":"Speech and dialogue systems","score":0.12110000103712082,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0608999989926815,"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":0.6470999717712402},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.5892999768257141},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5856000185012817},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5264999866485596},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49720001220703125},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.44040000438690186},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.427700012922287},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.40540000796318054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336999773979187},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6470999717712402},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.5892999768257141},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5856000185012817},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5264999866485596},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49720001220703125},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.44040000438690186},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.427700012922287},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3903999924659729},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C93983250","wikidata":"https://www.wikidata.org/wiki/Q795053","display_name":"Cost estimate","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.13653","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.13653","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.13653","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.13653","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,22],"Multimodal":[3],"Large":[4],"Language":[5],"Models":[6],"(MLLMs)":[7],"have":[8],"substantially":[9],"driven":[10],"the":[11,82,98,105,126,131,138,144],"progress":[12],"of":[13,58,84],"autonomous":[14],"agents":[15,26],"for":[16,38,53],"Graphical":[17],"User":[18],"Interface":[19],"(GUI).":[20],"Nevertheless,":[21],"real-world":[23],"applications,":[24],"GUI":[25,54,161,168],"are":[27,123,135],"often":[28],"faced":[29],"with":[30,110,159,177],"non-stationary":[31],"environments,":[32],"leading":[33],"to":[34,71,80,88],"high":[35],"computational":[36],"costs":[37,134],"data":[39,132],"curation":[40],"and":[41,63,103,148,170,173],"policy":[42,65,106,127,139],"optimization.":[43,66,150],"In":[44],"this":[45],"report,":[46],"we":[47],"introduce":[48],"a":[49,73,85],"novel":[50],"MLLM-centered":[51],"framework":[52,156],"agents,":[55],"which":[56],"consists":[57],"two":[59],"components:":[60],"agentic-Q":[61,112],"estimation":[62],"step-wise":[64,78,95],"The":[67,91],"former":[68],"one":[69,93],"aims":[70],"optimize":[72],"Q-model":[74],"that":[75,118,130,154],"can":[76],"generate":[77],"values":[79],"evaluate":[81],"contribution":[83],"given":[86],"action":[87],"task":[89],"completion.":[90],"latter":[92],"takes":[94],"samples":[96],"from":[97,143],"state-action":[99,121],"trajectory":[100],"as":[101],"inputs,":[102],"optimizes":[104],"via":[107],"reinforcement":[108],"learning":[109],"our":[111,155],"model.":[113],"It":[114],"should":[115],"be":[116],"noticed":[117],"(i)":[119],"all":[120],"trajectories":[122],"produced":[124],"by":[125],"itself,":[128],"so":[129],"collection":[133],"manageable;":[136],"(ii)":[137],"update":[140],"is":[141],"decoupled":[142],"environment,":[145],"ensuring":[146],"stable":[147],"efficient":[149],"Empirical":[151],"evaluations":[152],"show":[153],"endows":[157],"Ovis2.5-9B":[158],"powerful":[160],"interaction":[162],"capabilities,":[163],"achieving":[164],"remarkable":[165],"performances":[166],"on":[167],"navigation":[169],"grounding":[171],"benchmarks":[172],"even":[174],"surpassing":[175],"contenders":[176],"larger":[178],"scales.":[179]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-18T00:00:00"}