{"id":"https://openalex.org/W7139139481","doi":"https://doi.org/10.1609/aaai.v40i43.40966","title":"History-Aware Reasoning for GUI Agents","display_name":"History-Aware Reasoning for GUI Agents","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7139139481","doi":"https://doi.org/10.1609/aaai.v40i43.40966"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i43.40966","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i43.40966","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40966/44927","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40966/44927","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130018821","display_name":"Ziwei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziwei Wang","raw_affiliation_strings":["Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, Zhejiang University\nCollege of Computer Science and Technology, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, Zhejiang University\nCollege of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Leyang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leyang Yang","raw_affiliation_strings":["Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, Zhejiang University\nCollege of Computer Science and Technology, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, Zhejiang University\nCollege of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103533293","display_name":"Xiaoxuan Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoxuan Tang","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100782531","display_name":"Sheng Zhou","orcid":"https://orcid.org/0009-0007-4215-5464"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Zhou","raw_affiliation_strings":["Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, Zhejiang University","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103155183","display_name":"Dajun Chen","orcid":"https://orcid.org/0009-0000-9532-7636"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dajun Chen","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130049590","display_name":"Wei Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Jiang","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129765700","display_name":"Yong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5130018821"],"corresponding_institution_ids":["https://openalex.org/I55712492"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92411383,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"43","first_page":"36448","last_page":"36456"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.3003000020980835,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.3003000020980835,"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":0.14749999344348907,"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/T12128","display_name":"AI in Service Interactions","score":0.0551999993622303,"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/bridging","display_name":"Bridging (networking)","score":0.5877000093460083},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5256999731063843},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.48069998621940613},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46050000190734863},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.4422000050544739},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.4253000020980835},{"id":"https://openalex.org/keywords/non-monotonic-logic","display_name":"Non-monotonic logic","score":0.4235999882221222},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.39899998903274536},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"Episodic memory","score":0.34139999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7843999862670898},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5877000093460083},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5680999755859375},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5256999731063843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4832000136375427},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48069998621940613},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.4235999882221222},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.34139999747276306},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.33799999952316284},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C182620335","wikidata":"https://www.wikidata.org/wiki/Q2852531","display_name":"Answer set programming","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2596000134944916},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i43.40966","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i43.40966","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40966/44927","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i43.40966","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i43.40966","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40966/44927","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6968186497688293,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7139139481.pdf","grobid_xml":"https://content.openalex.org/works/W7139139481.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Advances":[0],"in":[1,51,88,115,153],"Multimodal":[2],"Large":[3],"Language":[4],"Models":[5],"have":[6],"significantly":[7],"enhanced":[8],"Graphical":[9],"User":[10],"Interface":[11],"(GUI)":[12],"automation.":[13,117],"Equipping":[14],"GUI":[15,56,82,116,199],"agents":[16,83],"with":[17,45,201],"reliable":[18,206],"episodic":[19,141],"reasoning":[20,52,111,142,191],"capabilities":[21],"is":[22,73],"essential":[23],"for":[24,75],"bridging":[25],"the":[26,34,64,76,93,103,107,177,189,198,220],"gap":[27],"between":[28],"users\u2019":[29],"concise":[30],"task":[31],"descriptions":[32],"and":[33,68,139,169,205,222],"complexities":[35],"of":[36,102,208,216,224],"real-world":[37],"execution.":[38],"Current":[39],"methods":[40],"integrate":[41],"Reinforcement":[42],"Learning":[43],"(RL)":[44],"System-2":[46],"Chain-of-Thought,":[47],"yielding":[48],"notable":[49],"gains":[50],"enhancement.":[53],"For":[54],"long-horizon":[55,154],"tasks,":[57],"historical":[58,104],"interactions":[59,95,105],"connect":[60],"each":[61],"screen":[62,98,209],"to":[63,133,195],"goal-oriented":[65],"episode":[66],"chain,":[67],"effectively":[69],"leveraging":[70],"these":[71],"clues":[72],"crucial":[74],"current":[77],"decision.":[78],"However,":[79],"existing":[80],"native":[81,183],"exhibit":[84],"weak":[85],"short-term":[86,151,203],"memory":[87,152,204],"their":[89,113],"explicit":[90],"reasoning,":[91],"interpreting":[92],"chained":[94],"as":[96],"discrete":[97],"understanding,":[99],"i.e.,":[100],"unawareness":[101],"within":[106],"episode.":[108],"This":[109],"history-agnostic":[110,194],"challenges":[112],"performance":[114],"To":[118],"alleviate":[119],"this":[120],"weakness,":[121],"we":[122,180],"propose":[123],"a":[124,161,171,182,214],"History-Aware":[125],"Reasoning":[126],"(HAR)":[127],"framework,":[128,179],"which":[129,187],"encourages":[130],"an":[131],"agent":[132,200],"reflect":[134],"on":[135],"its":[136],"own":[137],"errors":[138],"acquire":[140],"knowledge":[143],"from":[144,193],"them":[145],"via":[146],"tailored":[147,166],"strategies":[148],"that":[149],"enhance":[150],"interaction.":[155],"The":[156],"framework":[157],"mainly":[158],"comprises":[159],"constructing":[160],"reflective":[162],"learning":[163],"scenario,":[164],"synthesizing":[165],"correction":[167],"guidelines,":[168],"designing":[170],"hybrid":[172],"RL":[173],"reward":[174],"function.":[175],"Using":[176],"HAR":[178],"develop":[181],"end-to-end":[184],"model,":[185],"HAR-GUI-3B,":[186],"alters":[188],"inherent":[190],"mode":[192],"history-aware,":[196],"equipping":[197],"stable":[202],"perception":[207],"details.":[210],"Comprehensive":[211],"evaluations":[212],"across":[213],"range":[215],"GUI-related":[217],"benchmarks":[218],"demonstrate":[219],"effectiveness":[221],"generalization":[223],"our":[225],"method.":[226]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-03-20T00:00:00"}