{"id":"https://openalex.org/W7154948584","doi":"https://doi.org/10.48550/arxiv.2604.16004","title":"AgentV-RL: Scaling Reward Modeling with Agentic Verifier","display_name":"AgentV-RL: Scaling Reward Modeling with Agentic Verifier","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7154948584","doi":"https://doi.org/10.48550/arxiv.2604.16004"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.16004","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16004","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.2604.16004","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134051712","display_name":"Jiazheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiazheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134058445","display_name":"Ziche Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Ziche","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134033053","display_name":"Zhiheng Xi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi, Zhiheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101471591","display_name":"Wenqing Jing","orcid":"https://orcid.org/0009-0007-9306-8854"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing, Wenqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109693861","display_name":"Mingxu Chai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chai, Mingxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134037593","display_name":"Wei He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134048985","display_name":"Guoqiang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Guoqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134010067","display_name":"Chenghao Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Chenghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055648957","display_name":"Chenxin An","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"An, Chenxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687444","display_name":"Wenxiang Chen","orcid":"https://orcid.org/0000-0002-6499-3369"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wenxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134082301","display_name":"Zhicheng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134030458","display_name":"Haojie Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Haojie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125146388","display_name":"Dingwei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Dingwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134055817","display_name":"Tao Gui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gui, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134066240","display_name":"Qi Zhang","orcid":"https://orcid.org/0009-0006-7434-7148"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134082216","display_name":"Xuanjing Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Xuanjing","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/T10028","display_name":"Topic Modeling","score":0.2328999936580658,"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/T10028","display_name":"Topic Modeling","score":0.2328999936580658,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.1965000033378601,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.13699999451637268,"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/process","display_name":"Process (computing)","score":0.5839999914169312},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.5699999928474426},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.49219998717308044},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.48590001463890076},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4205999970436096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573000192642212},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5839999914169312},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.5699999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5210000276565552},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40380001068115234},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34940001368522644},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2732999920845032}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.16004","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16004","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.2604.16004","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16004","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Verifiers":[0],"have":[1],"been":[2],"demonstrated":[3],"to":[4,28,79],"enhance":[5],"LLM":[6],"reasoning":[7,25],"via":[8],"test-time":[9],"scaling":[10],"(TTS).":[11],"Yet,":[12],"they":[13],"face":[14],"significant":[15],"challenges":[16],"in":[17],"complex":[18],"domains.":[19],"Error":[20],"propagation":[21],"from":[22,77],"incorrect":[23],"intermediate":[24],"can":[26],"lead":[27],"false":[29],"positives":[30],"for":[31,154],"seemingly":[32],"plausible":[33],"solutions,":[34],"while":[35,81],"lacking":[36],"external":[37],"grounding":[38],"makes":[39],"verifiers":[40],"unreliable":[41],"on":[42],"computation":[43],"or":[44],"knowledge-intensive":[45],"tasks.":[46],"To":[47,102],"address":[48],"these":[49],"challenges,":[50],"we":[51,106],"propose":[52,107],"Agentic":[53,127],"Verifier,":[54],"a":[55,62,94,151],"framework":[56],"that":[57,126],"transforms":[58],"reward":[59,156],"modeling":[60],"into":[61],"multi-turn,":[63],"tool-augmented":[64],"deliberative":[65],"process.":[66],"We":[67],"introduce":[68],"complementary":[69],"forward":[70],"and":[71,97,112,136],"backward":[72],"agents:":[73],"one":[74],"traces":[75],"solutions":[76],"premises":[78],"conclusions,":[80],"the":[82,115],"other":[83],"re-checks":[84],"conclusions":[85],"against":[86],"their":[87],"underlying":[88],"premises.":[89],"This":[90],"bidirectional":[91],"process":[92],"enables":[93],"comprehensive,":[95],"reliable,":[96],"interpretable":[98],"assessment":[99],"of":[100],"solutions.":[101],"facilitate":[103],"practical":[104],"deployment,":[105],"AgentV-RL.":[108],"Through":[109],"proactive":[110],"exploration":[111],"reinforcement":[113],"learning,":[114],"verifier":[116],"autonomously":[117],"interleaves":[118],"tool-use":[119],"with":[120],"internal":[121],"reasoning.":[122],"Extensive":[123],"experiments":[124],"show":[125],"Verifier":[128],"yields":[129],"consistent":[130],"performance":[131],"gains":[132],"under":[133],"both":[134],"parallel":[135],"sequential":[137],"TTS.":[138],"Notably,":[139],"our":[140],"4B":[141],"variant":[142],"surpasses":[143],"state-of-the-art":[144],"ORMs":[145],"by":[146],"25.2%,":[147],"positioning":[148],"it":[149],"as":[150],"promising":[152],"paradigm":[153],"agentic":[155],"modeling.":[157]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-21T00:00:00"}