{"id":"https://openalex.org/W7166827193","doi":"https://doi.org/10.18653/v1/2026.findings-acl.581","title":"HiSA: Hierarchical State Abstraction for Scalable GUI Agents","display_name":"HiSA: Hierarchical State Abstraction for Scalable GUI Agents","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166827193","doi":"https://doi.org/10.18653/v1/2026.findings-acl.581"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.581","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.581","pdf_url":"https://aclanthology.org/2026.findings-acl.581.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.581.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058533932","display_name":"Weiming Li","orcid":"https://orcid.org/0009-0007-5204-4418"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Weiming Li","raw_affiliation_strings":["School of Computer Science and Engineering The University of New South Wales Sydney , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering The University of New South Wales Sydney , Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018724341","display_name":"Hye-Young Paik","orcid":"https://orcid.org/0000-0003-4425-7388"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hye-young Paik","raw_affiliation_strings":["School of Computer Science and Engineering The University of New South Wales Sydney , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering The University of New South Wales Sydney , Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053058502","display_name":"Yulei Sui","orcid":"https://orcid.org/0000-0002-9510-6574"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yulei Sui","raw_affiliation_strings":["School of Computer Science and Engineering The University of New South Wales Sydney , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering The University of New South Wales Sydney , Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81681562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11965","last_page":"11985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.414000004529953,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.414000004529953,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.10130000114440918,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.09160000085830688,"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/abstraction","display_name":"Abstraction","score":0.5842999815940857},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5073000192642212},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4616999924182892},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.28349998593330383},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2822999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013000249862671},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5842999815940857},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.581","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.581","pdf_url":"https://aclanthology.org/2026.findings-acl.581.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.581","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.581","pdf_url":"https://aclanthology.org/2026.findings-acl.581.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166827193.pdf","grobid_xml":"https://content.openalex.org/works/W7166827193.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"GUI":[1],"agents":[2],"generally":[3],"operate":[4],"on":[5,22],"raw":[6,31,68],"visual":[7],"and":[8,79,98,125],"textual":[9],"observations,":[10],"which":[11],"creates":[12],"a":[13,51,71,111,115],"fundamental":[14],"scalability":[15],"challenge.While":[16],"current":[17],"state-of-the-art":[18],"frameworks":[19],"predominantly":[20],"rely":[21],"inference-intensive":[23],"test-time":[24],"scaling":[25],"or":[26],"the":[27,39,132],"accumulation":[28],"of":[29,74],"unbounded":[30],"logs":[32],"to":[33,42,131],"maintain":[34],"task":[35],"coherence,":[36],"we":[37,48],"attribute":[38],"underlying":[40],"bottleneck":[41],"insufficient":[43],"state":[44,53],"abstraction.To":[45],"address":[46],"this,":[47],"propose":[49],"HiSA,":[50],"hierarchical":[52],"abstraction":[54],"approach":[55,109],"that":[56],"actively":[57],"restructures":[58],"knowledge":[59],"rather":[60],"than":[61],"passively":[62],"retaining":[63],"historical":[64],"information":[65],"by":[66,123,128],"organizing":[67],"histories":[69,103],"into":[70,85],"three-level":[72],"hierarchy":[73],"abstracted":[75],"steps,":[76],"refined":[77],"contexts,":[78],"induced":[80],"patterns.By":[81],"synthesizing":[82],"highdimensional":[83],"observations":[84],"compact":[86],"semantic":[87],"states,":[88],"HiSA":[89],"decouples":[90],"reasoning":[91],"efficacy":[92],"from":[93],"context":[94],"length,":[95],"enabling":[96],"precise":[97],"scalable":[99],"decision-making":[100],"as":[101],"interaction":[102],"grow.When":[104],"evaluating":[105],"using":[106],"Spider2-V,":[107],"our":[108],"establishes":[110],"new":[112],"state-of-the-art,":[113],"achieving":[114],"40.58%":[116],"success":[117],"rate":[118],"while":[119],"reducing":[120],"token":[121],"consumption":[122],"69.85%":[124],"monetary":[126],"costs":[127],"55.10%":[129],"compared":[130],"bestperforming":[133],"baseline.":[134]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}