{"id":"https://openalex.org/W7128680965","doi":"https://doi.org/10.48448/38sf-hg25","title":"GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning","display_name":"GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7128680965","doi":"https://doi.org/10.48448/38sf-hg25"},"language":"en","primary_location":{"id":"doi:10.48448/38sf-hg25","doi":"https://doi.org/10.48448/38sf-hg25","is_oa":true,"landing_page_url":"https://doi.org/10.48448/38sf-hg25","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},"volume":null,"type":"other","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/38sf-hg25","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125741655","display_name":"Association for Artificial Intelligence 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Artificial Intelligence 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125702053","display_name":"Junqi Gao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Junqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125721230","display_name":"Xiu Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125766128","display_name":"Dong Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125712976","display_name":"Runze Liu","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":"Liu, Runze","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067453635","display_name":"Jiafei Lyu","orcid":"https://orcid.org/0000-0001-6616-417X","observed_orcids":["https://orcid.org/0000-0001-6616-417X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Jiafei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113291945","display_name":"Biqing Qi","orcid":"https://orcid.org/0000-0002-4072-0577","observed_orcids":["https://orcid.org/0000-0002-4072-0577"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi, Biqing","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065103659","display_name":"Zhouyi Qian","orcid":"https://orcid.org/0009-0001-2329-0085","observed_orcids":["https://orcid.org/0009-0001-2329-0085"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Zhouyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101999478","display_name":"Kaiyan Zhang","orcid":"https://orcid.org/0000-0002-8059-1124","observed_orcids":["https://orcid.org/0000-0002-8059-1124"]},"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":"Zhang, Kaiyan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125712287","display_name":"Jian Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125739192","display_name":"Zhimu Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zhimu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5107301009","display_name":"Bowen Zhou","orcid":"https://orcid.org/0009-0003-4594-3432","observed_orcids":["https://orcid.org/0009-0003-4594-3432"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Bowen","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.45559999346733093,"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":0.45559999346733093,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.12839999794960022,"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/T10260","display_name":"Software Engineering Research","score":0.03620000183582306,"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/process-reward-models","display_name":"process reward models","score":0.9950000047683716},{"id":"https://openalex.org/keywords/generative-reasoning","display_name":"generative reasoning","score":0.6010000109672546},{"id":"https://openalex.org/keywords/chain-of-thought-reasoning","display_name":"chain-of-thought reasoning","score":0.8679999709129333},{"id":"https://openalex.org/keywords/code-verification","display_name":"code verification","score":0.8870000243186951},{"id":"https://openalex.org/keywords/process-supervision","display_name":"process supervision","score":0.6869999766349792},{"id":"https://openalex.org/keywords/test-time-compute-scaling","display_name":"test-time compute scaling","score":0.7229999899864197},{"id":"https://openalex.org/keywords/mathematical-reasoning","display_name":"mathematical reasoning","score":0.7710000276565552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7664999961853027},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6597999930381775},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5835000276565552},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5685999989509583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5656999945640564},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5591999888420105},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5354999899864197},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5091999769210815},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3424000144004822},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C76956256","wikidata":"https://www.wikidata.org/wiki/Q27610560","display_name":"Process modeling","level":3,"score":0.3237000107765198},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C187179951","wikidata":"https://www.wikidata.org/wiki/Q7784616","display_name":"Thinking processes","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/38sf-hg25","doi":"https://doi.org/10.48448/38sf-hg25","is_oa":true,"landing_page_url":"https://doi.org/10.48448/38sf-hg25","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/38sf-hg25","doi":"https://doi.org/10.48448/38sf-hg25","is_oa":true,"landing_page_url":"https://doi.org/10.48448/38sf-hg25","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416036437","https://openalex.org/W4415067244","https://openalex.org/W7138075993","https://openalex.org/W7168379831","https://openalex.org/W4417026635","https://openalex.org/W4416401424","https://openalex.org/W6910895196","https://openalex.org/W4416949895","https://openalex.org/W4399597391","https://openalex.org/W4403365357"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,188],"Large":[3],"Language":[4],"Models":[5,17],"(LLMs)":[6],"have":[7],"shown":[8],"that":[9,75,111,125,179],"it":[10],"is":[11],"promising":[12],"to":[13,21,57,160],"utilize":[14],"Process":[15],"Reward":[16],"(PRMs)":[18],"as":[19,162],"verifiers":[20],"enhance":[22],"the":[23,49,59,181],"performance":[24],"of":[25,52,62],"LLMs.":[26,189],"However,":[27],"current":[28],"PRMs":[29,130,184],"face":[30],"three":[31],"key":[32],"challenges:":[33],"(1)":[34],"limited":[35],"process":[36,72,94,177],"supervision":[37,95,178],"and":[38,54,97,106,119,147,185],"generalization":[39],"capabilities,":[40],"(2)":[41],"dependence":[42],"on":[43,117,153],"scalar":[44],"value":[45],"prediction":[46],"without":[47],"leveraging":[48],"generative":[50,71],"abilities":[51,159],"LLMs,":[53],"(3)":[55],"inability":[56],"scale":[58],"test-time":[60,140],"compute":[61],"PRMs.":[63],"In":[64],"this":[65],"work,":[66],"we":[67,100],"introduce":[68],"GenPRM,":[69],"a":[70,107,142,148,163,173],"reward":[73],"model":[74,165,168],"performs":[76],"explicit":[77],"Chain-of-Thought":[78],"(CoT)":[79],"reasoning":[80,89,122],"with":[81,131],"code":[82,113],"verification":[83],"before":[84],"providing":[85],"judgment":[86],"for":[87,166,176],"each":[88],"step.":[90],"To":[91],"obtain":[92],"high-quality":[93],"labels":[96],"rationale":[98,108],"data,":[99],"propose":[101],"Relative":[102],"Progress":[103],"Estimation":[104],"(RPE)":[105],"synthesis":[109],"framework":[110],"incorporates":[112],"verification.":[114],"Experimental":[115],"results":[116],"ProcessBench":[118],"several":[120],"mathematical":[121],"tasks":[123],"show":[124],"GenPRM":[126,144,150,156],"significantly":[127],"outperforms":[128,145],"prior":[129],"only":[132],"\\textbf{23K}":[133],"training":[134],"data":[135],"from":[136],"\\textbf{MATH}":[137],"dataset.":[138],"Through":[139],"scaling,":[141],"\\textbf{1.5B}":[143],"\\textbf{GPT-4o},":[146],"\\textbf{7B}":[149],"surpasses":[151],"\\textbf{Qwen2.5-Math-PRM-72B}":[152],"ProcessBench.":[154],"Additionally,":[155],"demonstrates":[157],"strong":[158],"serve":[161],"critic":[164,186],"policy":[167],"refinement.":[169],"This":[170],"work":[171],"establishes":[172],"new":[174],"paradigm":[175],"bridges":[180],"gap":[182],"between":[183],"models":[187]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-13T00:00:00"}