{"id":"https://openalex.org/W4412945186","doi":"https://doi.org/10.18653/v1/2025.acl-long.775","title":"Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems","display_name":"Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945186","doi":"https://doi.org/10.18653/v1/2025.acl-long.775"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.775","doi":"https://doi.org/10.18653/v1/2025.acl-long.775","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.775","pdf_url":"https://aclanthology.org/2025.acl-long.775.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2025.acl-long.775.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087697296","display_name":"Hao Peng","orcid":"https://orcid.org/0000-0001-7318-1779","observed_orcids":["https://orcid.org/0000-0001-7318-1779"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Peng","raw_affiliation_strings":["Department of Computer Science and Technology , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113281911","display_name":"Yunjia Qi","orcid":"https://orcid.org/0009-0009-1836-8413","observed_orcids":["https://orcid.org/0009-0009-1836-8413"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjia Qi","raw_affiliation_strings":["Department of Computer Science and Technology , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100775956","display_name":"Xiaozhi Wang","orcid":"https://orcid.org/0000-0002-4290-9023","observed_orcids":["https://orcid.org/0000-0002-4290-9023","https://orcid.org/0000-0002-5727-143X"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaozhi Wang","raw_affiliation_strings":["Department of Computer Science and Technology , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040604135","display_name":"Zijun Yao","orcid":"https://orcid.org/0000-0003-3647-8770","observed_orcids":["https://orcid.org/0000-0003-3647-8770"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijun Yao","raw_affiliation_strings":["Department of Computer Science and Technology , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bin Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Xu","raw_affiliation_strings":["Department of Computer Science and Technology , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Hou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Hou","raw_affiliation_strings":["Department of Computer Science and Technology , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003324011","display_name":"Juanzi Li","orcid":"https://orcid.org/0000-0002-6244-0664","observed_orcids":["https://orcid.org/0000-0002-6244-0664"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juanzi Li","raw_affiliation_strings":["Department of Computer Science and Technology , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.8993,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85474391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"15934","last_page":"15949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9496999979019165,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9496999979019165,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.0024999999441206455,"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/human-preferences","display_name":"human preferences","score":0.8289999961853027},{"id":"https://openalex.org/keywords/reward-systems","display_name":"reward systems","score":0.5370000004768372},{"id":"https://openalex.org/keywords/ai-alignment","display_name":"AI alignment","score":0.42100000381469727},{"id":"https://openalex.org/keywords/preference-elicitation","display_name":"preference elicitation","score":0.5920000076293945},{"id":"https://openalex.org/keywords/correctness-verification","display_name":"correctness verification","score":0.3330000042915344}],"concepts":[{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.8572783470153809},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8293898701667786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271374464035034},{"id":"https://openalex.org/C143661069","wikidata":"https://www.wikidata.org/wiki/Q670713","display_name":"Reward system","level":2,"score":0.5189342498779297},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32295873761177063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32228973507881165},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18204167485237122},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13032573461532593},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.10545304417610168},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06877133250236511},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.775","doi":"https://doi.org/10.18653/v1/2025.acl-long.775","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.775","pdf_url":"https://aclanthology.org/2025.acl-long.775.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.19328","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.19328","pdf_url":"https://arxiv.org/pdf/2502.19328","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.19328","doi":"https://doi.org/10.48550/arxiv.2502.19328","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.19328","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":"doi:10.18653/v1/2025.acl-long.775","doi":"https://doi.org/10.18653/v1/2025.acl-long.775","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.775","pdf_url":"https://aclanthology.org/2025.acl-long.775.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G7834717877","display_name":null,"funder_award_id":"62476150","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945186.pdf","grobid_xml":"https://content.openalex.org/works/W4412945186.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7102403975","https://openalex.org/W4417538704","https://openalex.org/W7102415536","https://openalex.org/W4403755005","https://openalex.org/W4414791307","https://openalex.org/W7166840538","https://openalex.org/W4416512539","https://openalex.org/W7134031930","https://openalex.org/W7131433391","https://openalex.org/W4407632903"],"abstract_inverted_index":{"Reward":[0],"models":[1,15,19,50],"(RMs)":[2],"are":[3,140],"crucial":[4],"for":[5],"the":[6,124],"training":[7,35,114],"and":[8,79,95,119],"inference-time":[9],"scaling":[10],"up":[11],"of":[12],"large":[13],"language":[14],"(LLMs).However,":[16],"existing":[17,91],"reward":[18,42,45,49,65,92,107,137],"primarily":[20],"focus":[21],"on":[22,90,100,130],"human":[23,71],"preferences,":[24],"neglecting":[25],"verifiable":[26,52,76],"correctness":[27,53],"signals":[28,54],"which":[29],"have":[30],"shown":[31],"strong":[32],"potential":[33],"in":[34],"LLMs.In":[36],"this":[37],"paper,":[38],"we":[39],"propose":[40],"agentic":[41],"modeling,":[43],"a":[44,64],"system":[46],"that":[47,69],"combines":[48,70],"with":[51,74,123],"from":[55],"different":[56],"aspects":[57],"to":[58,82,135,143],"provide":[59,83],"reliable":[60,85],"rewards.We":[61,86],"empirically":[62],"implement":[63],"agent,":[66],"named":[67],"REWARDAGENT,":[68],"preference":[72,115],"rewards":[73],"two":[75],"signals:":[77],"factuality":[78],"instruction":[80],"following,":[81],"more":[84],"conduct":[87],"comprehensive":[88],"experiments":[89],"model":[93],"benchmarks":[94,133],"inference":[96],"time":[97],"best-of-n":[98],"searches":[99],"real-world":[101],"downstream":[102],"tasks.RE-WARDAGENT":[103],"significantly":[104],"outperforms":[105],"vanilla":[106],"models,":[108],"demonstrating":[109],"its":[110],"effectiveness.We":[111],"further":[112,145],"construct":[113],"pairs":[116],"using":[117],"REWARDAGENT":[118],"train":[120],"an":[121],"LLM":[122],"DPO":[125],"objective,":[126],"achieving":[127],"superior":[128],"performance":[129],"various":[131],"NLP":[132],"compared":[134],"conventional":[136],"models.Our":[138],"codes":[139],"publicly":[141],"released":[142],"facilitate":[144],"research":[146],"1":[147],".":[148]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-10T00:00:00"}