{"id":"https://openalex.org/W7225201003","doi":"https://doi.org/10.48550/arxiv.2611.02566","title":"CR-Bench-v2: Evaluating the Real-World Utility of AI Code Review Agents","display_name":"CR-Bench-v2: Evaluating the Real-World Utility of AI Code Review Agents","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225201003","doi":"https://doi.org/10.48550/arxiv.2611.02566"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.02566","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02566","pdf_url":"https://arxiv.org/pdf/2611.02566","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.02566","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014954666","display_name":"Kristen Pereira","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153414","display_name":"Nutanix (United States)","ror":"https://ror.org/04tz2xx73","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153414"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pereira, Kristen","raw_affiliation_strings":["Nutanix, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nutanix, Inc","institution_ids":["https://openalex.org/I4210153414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007979497","display_name":"Neelabh Sinha","orcid":"https://orcid.org/0000-0002-0945-4696","observed_orcids":["https://orcid.org/0000-0002-0945-4696"]},"institutions":[{"id":"https://openalex.org/I4210153414","display_name":"Nutanix (United States)","ror":"https://ror.org/04tz2xx73","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153414"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sinha, Neelabh","raw_affiliation_strings":["Nutanix, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nutanix, Inc","institution_ids":["https://openalex.org/I4210153414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043902598","display_name":"Rajat Ghosh","orcid":"https://orcid.org/0000-0003-2919-9693","observed_orcids":["https://orcid.org/0000-0003-2919-9693"]},"institutions":[{"id":"https://openalex.org/I4210153414","display_name":"Nutanix (United States)","ror":"https://ror.org/04tz2xx73","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153414"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghosh, Rajat","raw_affiliation_strings":["Nutanix, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nutanix, Inc","institution_ids":["https://openalex.org/I4210153414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113845539","display_name":"Debojyoti Dutta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153414","display_name":"Nutanix (United States)","ror":"https://ror.org/04tz2xx73","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153414"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dutta, Debojyoti","raw_affiliation_strings":["Nutanix, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nutanix, Inc","institution_ids":["https://openalex.org/I4210153414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210153414"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/automated-code-review","display_name":"automated code review","score":0.9829999804496765},{"id":"https://openalex.org/keywords/defect-detection","display_name":"defect detection","score":0.7760000228881836},{"id":"https://openalex.org/keywords/pull-requests","display_name":"pull requests","score":0.7739999890327454},{"id":"https://openalex.org/keywords/reviewer-comments","display_name":"reviewer comments","score":0.5490000247955322},{"id":"https://openalex.org/keywords/swe-bench","display_name":"SWE-bench","score":0.7749999761581421},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.6079999804496765},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5239999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610999941825867},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6333000063896179},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.5561000108718872},{"id":"https://openalex.org/C160713754","wikidata":"https://www.wikidata.org/wiki/Q1389965","display_name":"Maintainability","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.4796000123023987},{"id":"https://openalex.org/C133237599","wikidata":"https://www.wikidata.org/wiki/Q2295111","display_name":"Code smell","level":5,"score":0.4702000021934509},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4553000032901764},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.39149999618530273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37630000710487366},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.33239999413490295},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31459999084472656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3077000081539154},{"id":"https://openalex.org/C10272871","wikidata":"https://www.wikidata.org/wiki/Q929972","display_name":"Software inspection","level":5,"score":0.2574999928474426},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.02566","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02566","pdf_url":"https://arxiv.org/pdf/2611.02566","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2611.02566","doi":"https://doi.org/10.48550/arxiv.2611.02566","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.02566","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.02566","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02566","pdf_url":"https://arxiv.org/pdf/2611.02566","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225201003.pdf","grobid_xml":"https://content.openalex.org/works/W7225201003.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2948096068","https://openalex.org/W4308643152","https://openalex.org/W4411271494","https://openalex.org/W4416692581","https://openalex.org/W7075994024","https://openalex.org/W7119523234","https://openalex.org/W7125193990","https://openalex.org/W7133222210","https://openalex.org/W7135192568"],"related_works":["https://openalex.org/W7135169507","https://openalex.org/W7221505180","https://openalex.org/W7140294178","https://openalex.org/W7224086255","https://openalex.org/W7172262225","https://openalex.org/W7143378675","https://openalex.org/W7213345403","https://openalex.org/W4416692581","https://openalex.org/W7222836402","https://openalex.org/W6967101516"],"abstract_inverted_index":{"The":[0],"rapid":[1],"growth":[2],"of":[3,167,201],"automated":[4,13],"code":[5,14,17,47,176],"generation":[6],"has":[7],"created":[8],"a":[9,76,101,111,122,126,133],"pressing":[10],"need":[11],"for":[12,94,136],"review.":[15],"Yet":[16],"review":[18,48,58,86,168,177],"resists":[19],"full":[20,89],"automation:":[21],"it":[22],"depends":[23],"on":[24,29,34,40,55],"context":[25],"beyond":[26],"the":[27,30,157,165,194],"\\textit{diff},":[28],"author's":[31],"intent,":[32],"and":[33,38,52,68,97,132,140,160,207],"judgments":[35],"about":[36,199],"design":[37],"maintainability":[39],"which":[41,64,151,163],"even":[42],"expert":[43],"reviewers":[44],"disagree.":[45],"Existing":[46],"benchmarks":[49],"lack":[50],"standardization":[51],"rely":[53],"largely":[54],"noisy":[56],"human":[57],"comments":[59,169],"scored":[60],"with":[61,88,110,125],"text-similarity":[62],"metrics,":[63],"reward":[65],"surface":[66],"overlap":[67],"fail":[69],"to":[70,100],"measure":[71],"precision.":[72],"We":[73,142,173],"introduce":[74],"\\texttt{CR-Bench},":[75],"defect-centric":[77],"evaluation":[78],"framework":[79],"that":[80,170],"recasts":[81],"SWE-Bench":[82,117],"issues":[83],"as":[84],"pull-request":[85],"tasks":[87],"repository":[90],"context.":[91],"After":[92],"filtering":[93],"review-detectable":[95],"defects":[96,203],"grounding":[98],"each":[99],"single":[102],"originating":[103],"pull":[104,123],"request,":[105],"\\texttt{CR-Bench}":[106],"contains":[107],"584":[108],"instances,":[109],"174-instance":[112],"\\texttt{CR-Bench-Verified}":[113],"subset":[114],"derived":[115],"from":[116],"Verified.":[118],"Each":[119],"instance":[120],"pairs":[121],"request":[124],"known":[127,202],"defect,":[128,159],"its":[129],"ground-truth":[130],"fix,":[131],"taxonomy":[134],"label":[135],"bug":[137],"category,":[138],"impact,":[139],"severity.":[141],"propose":[143],"two":[144],"complementary":[145],"metrics:":[146],"\\emph{Known-Defect":[147],"Detection":[148],"Rate}":[149],"(KDDR),":[150],"measures":[152,164],"whether":[153],"an":[154],"agent":[155],"identifies":[156],"labeled":[158],"\\emph{Usefulness":[161],"Rate},":[162],"fraction":[166],"are":[171],"actionable.":[172],"evaluate":[174],"eight":[175],"agents":[178],"over":[179],"four":[180],"backbones,":[181],"plus":[182],"commercially":[183],"available":[184],"Gemini":[185,208],"Code":[186,209],"Assist,":[187],"using":[188],"three":[189],"independent":[190],"LLM":[191],"judges.":[192],"Even":[193],"strongest":[195],"systems":[196],"detect":[197],"only":[198],"one-third":[200],"(KDDR":[204],"$\\approx$":[205],"33\\%),":[206],"Assist":[210],"detects":[211],"8.1\\%.":[212]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-11-04T00:00:00"}