{"id":"https://openalex.org/W7135141069","doi":"https://doi.org/10.48550/arxiv.2603.10178","title":"Video-Based Reward Modeling for Computer-Use Agents","display_name":"Video-Based Reward Modeling for Computer-Use Agents","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7135141069","doi":"https://doi.org/10.48550/arxiv.2603.10178"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.10178","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10178","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":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.2603.10178","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128893780","display_name":"Linxin Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Linxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128825524","display_name":"Jieyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jieyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120309106","display_name":"Huanxin Sheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng, Huanxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128824750","display_name":"Taiwei Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Taiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128866006","display_name":"Gupta Rahul","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rahul, Gupta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128899850","display_name":"Yang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128803578","display_name":"Ranjay Krishna","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krishna, Ranjay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128835654","display_name":"Jian Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128894771","display_name":"Jieyu Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jieyu","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":0.19789999723434448,"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":0.19789999723434448,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.10050000250339508,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.093299999833107,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6802999973297119},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5978999733924866},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5885999798774719},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5706999897956848},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.49470001459121704},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.47119998931884766},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4323999881744385},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.40380001068115234},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.38359999656677246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8461999893188477},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6802999973297119},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5978999733924866},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5885999798774719},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5706999897956848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5623000264167786},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.49470001459121704},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4323999881744385},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39340001344680786},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38359999656677246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36469998955726624},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.27379998564720154},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.10178","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10178","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.10178","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10178","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Computer-using":[0],"agents":[1],"(CUAs)":[2],"are":[3],"becoming":[4],"increasingly":[5],"capable;":[6],"however,":[7],"it":[8,56],"remains":[9],"difficult":[10],"to":[11,91,145],"scale":[12],"evaluation":[13],"of":[14,35,44,80],"whether":[15],"a":[16,20,33,78,138,142,193],"trajectory":[17,40],"truly":[18],"fulfills":[19],"user":[21,139],"instruction.":[22],"In":[23],"this":[24],"work,":[25],"we":[26,106,127],"study":[27],"reward":[28,188],"modeling":[29,53,189],"from":[30,37,101],"execution":[31,104],"video:":[32],"sequence":[34,144],"keyframes":[36],"an":[38,129],"agent":[39],"that":[41,68,135,186],"is":[42,54],"independent":[43],"the":[45],"agent's":[46],"internal":[47],"reasoning":[48],"or":[49],"actions.":[50],"Although":[51],"video-execution":[52,143,159,187],"method-agnostic,":[55],"presents":[57],"key":[58],"challenges,":[59],"including":[60],"highly":[61],"redundant":[62],"layouts":[63],"and":[64,115,141,155,168,175],"subtle,":[65],"localized":[66],"cues":[67],"determine":[69],"success.":[70,148],"We":[71,85],"introduce":[72],"Execution":[73,130],"Video":[74,131],"Reward":[75,132],"53k":[76,81],"(ExeVR-53k),":[77],"dataset":[79],"high-quality":[82],"video--task--reward":[83],"triplets.":[84],"further":[86],"propose":[87],"adversarial":[88],"instruction":[89,140],"translation":[90],"synthesize":[92],"negative":[93],"samples":[94],"with":[95],"step-level":[96],"annotations.":[97],"To":[98],"enable":[99],"learning":[100],"long,":[102],"high-resolution":[103],"videos,":[105],"design":[107],"spatiotemporal":[108],"token":[109],"pruning,":[110],"which":[111],"removes":[112],"homogeneous":[113],"regions":[114],"persistent":[116],"tokens":[117],"while":[118,177],"preserving":[119],"decisive":[120],"UI":[121],"changes.":[122],"Building":[123],"on":[124,158],"these":[125],"components,":[126],"fine-tune":[128],"Model":[133],"(ExeVRM)":[134],"takes":[136],"only":[137],"predict":[146],"task":[147],"Our":[149],"ExeVRM":[150],"8B":[151],"achieves":[152],"84.7%":[153],"accuracy":[154],"87.7%":[156],"recall":[157],"assessment,":[160],"outperforming":[161],"strong":[162],"proprietary":[163],"models":[164],"such":[165],"as":[166,192],"GPT-5.2":[167],"Gemini-3":[169],"Pro":[170],"across":[171],"Ubuntu,":[172],"macOS,":[173],"Windows,":[174],"Android,":[176],"providing":[178],"more":[179],"precise":[180],"temporal":[181],"attribution.":[182],"These":[183],"results":[184],"show":[185],"can":[190],"serve":[191],"scalable,":[194],"model-agnostic":[195],"evaluator":[196],"for":[197],"CUAs.":[198]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-13T00:00:00"}