{"id":"https://openalex.org/W7169795977","doi":"https://doi.org/10.48550/arxiv.2607.15388","title":"Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning","display_name":"Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7169795977","doi":"https://doi.org/10.48550/arxiv.2607.15388"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.15388","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15388","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":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.2607.15388","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045341412","display_name":"Chih-Hsuan Yang","orcid":"https://orcid.org/0000-0003-4841-1135"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Chih-Hsuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127101963","display_name":"J Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jingyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141185249","display_name":"Vikram Vasudevan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasudevan, Vikram","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101696232","display_name":"Cheng-Hau Yang","orcid":"https://orcid.org/0000-0002-1149-3686"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Cheng-Hau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141178884","display_name":"Huihuo Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Huihuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141210582","display_name":"Le Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Le","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059877418","display_name":"E. A. Huerta","orcid":"https://orcid.org/0000-0002-9682-3604"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huerta, Eliu A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141167783","display_name":"Venkatram Vishwanath","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vishwanath, Venkatram","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133096475","display_name":"Ian T. Foster","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Foster, Ian T.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014920685","display_name":"Rajeev Thakur","orcid":"https://orcid.org/0000-0002-5532-3048"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thakur, Rajeev","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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.2085999995470047,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.2085999995470047,"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/T10126","display_name":"Logic, programming, and type systems","score":0.13670000433921814,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.0575999990105629,"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/context","display_name":"Context (archaeology)","score":0.6546000242233276},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.6290000081062317},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6129999756813049},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.6111000180244446},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5706999897956848},{"id":"https://openalex.org/keywords/forcing","display_name":"Forcing (mathematics)","score":0.5277000069618225},{"id":"https://openalex.org/keywords/closing","display_name":"Closing (real estate)","score":0.4009999930858612}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6546000242233276},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.6290000081062317},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6129999756813049},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.6111000180244446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5985999703407288},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5706999897956848},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C101097943","wikidata":"https://www.wikidata.org/wiki/Q5176983","display_name":"Counterintuitive","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2971000075340271},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C133112747","wikidata":"https://www.wikidata.org/wiki/Q7251931","display_name":"Protocol analysis","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C23131810","wikidata":"https://www.wikidata.org/wiki/Q818574","display_name":"Observational study","level":2,"score":0.2712000012397766}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.15388","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15388","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":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.2607.15388","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15388","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.5686495900154114,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Many":[0],"math-":[1],"and":[2,125,137],"science-oriented":[3],"agent":[4],"systems":[5],"use":[6],"hierarchical":[7],"designs":[8],"with":[9],"specialized":[10],"reviewer":[11,80,99,103,134,155],"roles,":[12],"assuming":[13],"that":[14,133],"a":[15,68,177],"dedicated":[16],"review":[17],"stage":[18],"should":[19],"help":[20],"turn":[21],"wrong":[22],"candidates":[23],"into":[24],"correct":[25],"ones.":[26],"We":[27,72],"test":[28],"this":[29,57,75],"assumption":[30],"on":[31,43,195],"4,181":[32],"verifier-grounded":[33],"Omni-MATH":[34],"problems":[35,189],"using":[36],"matched":[37,144],"gpt-oss-120b":[38],"actors.":[39],"Collaboration":[40],"adds":[41],"little":[42],"the":[44,52,87,90,122,159,168],"easiest":[45],"tiers,":[46],"but":[47],"from":[48],"tier":[49],"4":[50],"onward":[51],"gains":[53],"open":[54],"sharply;":[55],"in":[56,158],"harder":[58],"regime,":[59],"broadcast-style":[60],"peer":[61],"discussion":[62],"reaches":[63],"higher":[64],"final":[65,151],"accuracy":[66],"than":[67,107],"planner-executor-reviewer":[69],"pipeline":[70],"(PER).":[71],"ask":[73],"whether":[74,84],"gap":[76],"is":[77,95,104,116],"explained":[78,97],"by":[79,83,98],"quality":[81,136],"or":[82],"critique":[85,115,138],"changes":[86],"next":[88,123],"answer":[89],"protocol":[91,178],"carries":[92],"forward.":[93],"It":[94],"not":[96,193],"precision":[100],"alone:":[101],"PER's":[102],"more":[105,188],"precise":[106],"broadcast's":[108],"(0.861":[109],"vs.":[110],"0.644),":[111],"yet":[112,183],"evaluator-verified":[113],"useful":[114],"much":[117],"less":[118],"likely":[119],"to":[120,186],"change":[121],"candidate":[124],"produces":[126],"lower":[127],"reviewer-guided":[128],"repair.":[129],"These":[130],"results":[131],"show":[132],"detection":[135],"uptake":[139],"are":[140],"empirically":[141],"separable.":[142],"Within":[143],"PER":[145],"interventions,":[146],"forcing":[147],"explicit":[148],"acknowledgment":[149],"lowers":[150],"accuracy,":[152],"while":[153],"embedding":[154],"guidance":[156],"directly":[157],"solver's":[160],"working":[161],"context":[162],"partially":[163],"improves":[164],"follow-through":[165],"without":[166],"closing":[167],"gap.":[169],"Overall,":[170],"reviewer-centric":[171],"evaluation":[172],"can":[173],"overstate":[174],"system":[175],"quality:":[176],"may":[179],"spot":[180],"errors":[181],"well":[182],"still":[184],"fail":[185],"solve":[187],"if":[190],"it":[191],"does":[192],"act":[194],"those":[196],"critiques.":[197]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-21T00:00:00"}
