{"id":"https://openalex.org/W4415538938","doi":"https://doi.org/10.1145/3746027.3755189","title":"PG-Agent: An Agent Powered by Page Graph","display_name":"PG-Agent: An Agent Powered by Page Graph","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538938","doi":"https://doi.org/10.1145/3746027.3755189"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755189","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5036783638","display_name":"W. Chen","orcid":"https://orcid.org/0009-0005-1953-1156"},"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":"Weizhi Chen","raw_affiliation_strings":["Zhejiang Key Lab of Accessible Perception &amp; Intelligent Systems, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-1953-1156","affiliations":[{"raw_affiliation_string":"Zhejiang Key Lab of Accessible Perception &amp; Intelligent Systems, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389386","display_name":"Ziwei Wang","orcid":"https://orcid.org/0000-0003-4479-3738"},"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":"Ziwei Wang","raw_affiliation_strings":["Zhejiang Key Lab of Accessible Perception &amp; Intelligent Systems, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4479-3738","affiliations":[{"raw_affiliation_string":"Zhejiang Key Lab of Accessible Perception &amp; Intelligent Systems, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Leyang Yang","orcid":"https://orcid.org/0009-0006-5553-8037"},"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":"Leyang Yang","raw_affiliation_strings":["Zhejiang Key Lab of Accessible Perception &amp; Intelligent Systems, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-5553-8037","affiliations":[{"raw_affiliation_string":"Zhejiang Key Lab of Accessible Perception &amp; Intelligent Systems, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102754272","display_name":"Sheng Zhou","orcid":"https://orcid.org/0000-0003-3645-1041"},"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 Lab of Accessible Perception &amp; Intelligent Systems, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3645-1041","affiliations":[{"raw_affiliation_string":"Zhejiang Key Lab of Accessible Perception &amp; Intelligent Systems, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"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, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-1765-9924","affiliations":[{"raw_affiliation_string":"Ant Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052757755","display_name":"Jiajun Bu","orcid":"https://orcid.org/0000-0002-1097-2044"},"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":"Jiajun Bu","raw_affiliation_strings":["Zhejiang Key Lab of Accessible Perception &amp; Intelligent Systems, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1097-2044","affiliations":[{"raw_affiliation_string":"Zhejiang Key Lab of Accessible Perception &amp; Intelligent Systems, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yong Li","orcid":"https://orcid.org/0009-0005-1664-6425"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-1664-6425","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067065175","display_name":"Wei Jiang","orcid":"https://orcid.org/0009-0003-6605-9793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Jiang","raw_affiliation_strings":["Ant Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-6605-9793","affiliations":[{"raw_affiliation_string":"Ant Group, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26228174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6878","last_page":"6887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12238","display_name":"Green IT and Sustainability","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T12238","display_name":"Green IT and Sustainability","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T11478","display_name":"Caching and Content Delivery","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/graphical-user-interface","display_name":"Graphical user interface","score":0.6538000106811523},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5515999794006348},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5062999725341797},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44190001487731934},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.4081000089645386},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.38040000200271606},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.3310999870300293},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.3151000142097473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820900022983551},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.6538000106811523},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5515999794006348},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4345000088214874},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3499999940395355},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3310999870300293},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30550000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C2984927552","wikidata":"https://www.wikidata.org/wiki/Q845734","display_name":"Graphical display","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755189","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G356681761","display_name":null,"funder_award_id":"62372408, 62476245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2963011053","https://openalex.org/W4393065402","https://openalex.org/W4401043213","https://openalex.org/W4401856679","https://openalex.org/W4402670856","https://openalex.org/W4402671930","https://openalex.org/W4402753874","https://openalex.org/W4404783040","https://openalex.org/W4405595839","https://openalex.org/W4412887860","https://openalex.org/W4415124086","https://openalex.org/W6889748593"],"related_works":[],"abstract_inverted_index":{"Graphical":[0],"User":[1],"Interface":[2],"(GUI)":[3],"agents":[4,13,29,59],"possess":[5],"significant":[6],"commercial":[7],"and":[8,11,66,123],"social":[9],"value,":[10],"GUI":[12,28,42,64,120],"powered":[14],"by":[15,98],"advanced":[16],"multimodal":[17],"large":[18],"language":[19],"models":[20],"(MLLMs)":[21],"have":[22],"demonstrated":[23],"remarkable":[24],"potential.":[25],"Currently,":[26],"existing":[27],"usually":[30],"utilize":[31,102],"sequential":[32,80],"episodes":[33,81,162],"of":[34,91,119,157],"multi-step":[35],"operations":[36],"across":[37],"pages":[38,93],"as":[39],"the":[40,48,58,63,79,88,92,103,139,155],"prior":[41],"knowledge,":[43],"which":[44,85],"fails":[45],"to":[46,60,68,77,113,135,146],"capture":[47],"complex":[49],"transition":[50],"relationship":[51],"between":[52],"pages,":[53],"making":[54],"it":[55,143],"challenging":[56],"for":[57,163],"deeply":[61],"perceive":[62],"environment":[65],"generalize":[67,145],"new":[69],"scenarios.":[70,148],"Therefore,":[71],"we":[72,106],"design":[73],"an":[74],"automated":[75],"pipeline":[76],"transform":[78],"into":[82],"page":[83,104,164],"graphs,":[84,105],"explicitly":[86],"model":[87],"graph":[89,165],"structure":[90],"that":[94,142],"are":[95],"naturally":[96],"connected":[97],"actions.":[99],"To":[100],"fully":[101],"further":[107],"introduce":[108],"Retrieval-Augmented":[109],"Generation":[110],"(RAG)":[111],"technology":[112],"effectively":[114],"retrieve":[115],"reliable":[116],"perception":[117],"guidelines":[118,140],"from":[121],"them,":[122],"a":[124],"tailored":[125],"multi-agent":[126],"framework":[127],"PG-Agent":[128],"with":[129,138,160],"task":[130],"decomposition":[131],"strategy":[132],"is":[133],"proposed":[134],"be":[136,170],"injected":[137],"so":[141],"can":[144],"unseen":[147],"Extensive":[149],"experiments":[150],"on":[151],"various":[152],"benchmarks":[153],"demonstrate":[154],"effectiveness":[156],"PG-Agent,":[158],"even":[159],"limited":[161],"construction.":[166],"Our":[167],"codes":[168],"will":[169],"publicly":[171],"available":[172],"at":[173],"https://github.com/chenwz-123/PG-Agent.":[174]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}
