{"id":"https://openalex.org/W7164174844","doi":"https://doi.org/10.48550/arxiv.2606.11078","title":"A History-Aware Visually Grounded Critic for Computer Use Agents","display_name":"A History-Aware Visually Grounded Critic for Computer Use Agents","publication_year":2026,"publication_date":"2026-06-09","ids":{"openalex":"https://openalex.org/W7164174844","doi":"https://doi.org/10.48550/arxiv.2606.11078"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.11078","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11078","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.11078","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138369809","display_name":"Jaewoo Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Jaewoo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138322551","display_name":"Zaid Khan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Zaid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039920828","display_name":"Archiki Prasad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prasad, Archiki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138388353","display_name":"Justin Chih-Yao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Justin Chih-Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101527369","display_name":"Supriyo Chakraborty","orcid":"https://orcid.org/0000-0003-3697-0044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chakraborty, Supriyo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138314925","display_name":"Kartik Balasubramaniam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balasubramaniam, Kartik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138362251","display_name":"Sambit Sahu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sahu, Sambit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038276570","display_name":"Elias Stengel-Eskin","orcid":"https://orcid.org/0000-0002-6689-505X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stengel-Eskin, Elias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138316440","display_name":"Hyunji Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Hyunji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138370543","display_name":"Mohit Bansal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bansal, Mohit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.1875,"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":0.1875,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.12049999833106995,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.08449999988079071,"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/grounded-theory","display_name":"Grounded theory","score":0.5249999761581421},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.498199999332428},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.45980000495910645},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.40849998593330383},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.3889999985694885},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.38440001010894775},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.38019999861717224},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3749000132083893}],"concepts":[{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.708899974822998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6818000078201294},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.5249999761581421},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3953000009059906},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3889999985694885},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.31790000200271606},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C2779018934","wikidata":"https://www.wikidata.org/wiki/Q1129653","display_name":"Everyday life","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2531999945640564},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.11078","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11078","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.11078","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11078","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7640625834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Various":[0],"test-time":[1,74,197],"interventions":[2],"for":[3,165,169,196],"Computer":[4],"Use":[5],"Agents":[6],"(CUAs),":[7],"including":[8],"critic":[9,80,107],"models,":[10],"have":[11],"been":[12],"developed":[13],"to":[14,55,86,95,113,136],"improve":[15],"performance":[16],"through":[17],"pre-execution":[18],"action":[19],"evaluation":[20],"in":[21,199],"complex":[22],"Graphical":[23],"User":[24],"Interface":[25],"(GUI)":[26],"environments.":[27],"However,":[28],"existing":[29,150],"critics":[30],"suffer":[31],"from":[32],"two":[33],"key":[34],"limitations:":[35],"they":[36],"(1)":[37],"focus":[38],"primarily":[39],"on":[40,82],"short-sighted":[41,182],"decision":[42,111],"loops":[43],"(e.g.,":[44,59],"forgetting":[45],"earlier":[46],"actions)":[47],"and":[48,94,123,144,152,167,171,184],"(2)":[49],"lack":[50],"the":[51,106,109,119,133,160],"visual":[52,99],"grounding":[53],"needed":[54],"detect":[56],"flawed":[57],"actions":[58,97],"clicking":[60],"wrong":[61],"UI":[62],"elements).":[63],"To":[64],"address":[65],"these,":[66],"we":[67],"introduce":[68],"HiViG,":[69],"a":[70,78,91],"History-aware":[71],"Visually":[72],"Grounded":[73],"framework,":[75],"built":[76],"around":[77],"multimodal":[79],"trained":[81],"real":[83],"GUI":[84,201],"trajectories":[85],"abstract":[87],"past":[88],"interactions":[89],"into":[90,108],"compact":[92],"record":[93],"evaluate":[96],"with":[98,191],"grounding.":[100],"At":[101],"test":[102],"time,":[103],"HiViG":[104,147],"integrates":[105],"policy":[110],"loop":[112],"provide":[114],"macro-action":[115,179],"history,":[116],"which":[117,127],"summarizes":[118],"policy's":[120],"completed":[121],"achievements,":[122],"visually":[124,185],"grounded":[125,186],"critique,":[126],"verifies":[128],"raw":[129],"execution":[130,189],"coordinates":[131],"against":[132],"current":[134],"screenshot":[135],"intercept":[137],"errors":[138],"before":[139],"execution.":[140],"Across":[141],"web,":[142],"mobile,":[143],"desktop":[145],"benchmarks,":[146],"consistently":[148],"outperforms":[149],"scalar":[151],"verbal":[153],"critics,":[154],"improving":[155],"average":[156],"success":[157],"rates":[158],"over":[159],"strongest":[161],"baseline":[162],"by":[163],"5.8%":[164],"Qwen3-VL-32B":[166],"9.0%":[168],"Gemini-3-Flash,":[170],"demonstrates":[172],"strong":[173],"cross-platform":[174],"generalization.":[175],"Ablations":[176],"show":[177],"that":[178],"history":[180],"mitigates":[181],"planning":[183],"critique":[187],"reduces":[188],"errors,":[190],"both":[192],"components":[193],"being":[194],"critical":[195],"scaling":[198],"long-horizon":[200],"tasks.":[202]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-11T00:00:00"}