{"id":"https://openalex.org/W7166886770","doi":"https://doi.org/10.18653/v1/2026.acl-long.1292","title":"Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards","display_name":"Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166886770","doi":"https://doi.org/10.18653/v1/2026.acl-long.1292"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1292","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1292","pdf_url":"https://aclanthology.org/2026.acl-long.1292.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1292.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005645757","display_name":"Raffaele Pisano","orcid":"https://orcid.org/0000-0002-8040-5088"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raffaele Pisano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026648049","display_name":"Roberto Navigli","orcid":"https://orcid.org/0000-0003-3831-9706"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Navigli","raw_affiliation_strings":["Babelscape & Sapienza University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Babelscape & Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88280747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28022","last_page":"28042"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.7748000025749207,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.7748000025749207,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.015699999406933784,"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/T11719","display_name":"Data Quality and Management","score":0.010099999606609344,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6467000246047974},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.45899999141693115},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.34470000863075256},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3066999912261963},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.28679999709129333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6898999810218811},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6467000246047974},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4207000136375427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3709000051021576},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33959999680519104},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C76956256","wikidata":"https://www.wikidata.org/wiki/Q27610560","display_name":"Process modeling","level":3,"score":0.24560000002384186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1292","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1292","pdf_url":"https://aclanthology.org/2026.acl-long.1292.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1292","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1292","pdf_url":"https://aclanthology.org/2026.acl-long.1292.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.4789566695690155,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166886770.pdf","grobid_xml":"https://content.openalex.org/works/W7166886770.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Process":[0],"Reward":[1],"Models":[2,21],"(PRMs)":[3],"have":[4],"emerged":[5],"as":[6,123],"a":[7,59,85,134],"powerful":[8],"tool":[9],"for":[10,139,147],"providing":[11],"step-level":[12],"feedback":[13],"when":[14,33],"evaluating":[15],"the":[16,34,54,75,151],"reasoning":[17,91],"of":[18,27,87],"Large":[19],"Language":[20,79],"(LLMs),":[22],"which":[23],"frequently":[24],"produce":[25],"chains":[26],"thought":[28],"(CoTs)":[29],"containing":[30],"errors":[31],"even":[32],"final":[35],"answer":[36],"is":[37],"correct.However,":[38],"existing":[39],"PRM":[40,65,108],"datasets":[41,110],"remain":[42],"expensive":[43],"to":[44,47,53,64,100],"construct,":[45],"prone":[46],"annotation":[48],"errors,":[49],"and":[50,61,97,120,136,143],"predominantly":[51],"limited":[52],"mathematical":[55,119,153],"domain.This":[56],"work":[57],"introduces":[58],"novel":[60],"scalable":[62,135],"approach":[63],"dataset":[66],"generation":[67],"based":[68],"on":[69],"planning":[70,131],"logical":[71],"problems":[72,132],"expressed":[73],"in":[74,117],"Planning":[76],"Domain":[77],"Definition":[78],"(PDDL).Using":[80],"this":[81,157],"method,":[82],"we":[83],"generate":[84],"corpus":[86],"approximately":[88],"one":[89],"million":[90],"steps":[92],"across":[93,125],"various":[94],"PDDL":[95],"domains":[96],"use":[98],"it":[99],"train":[101],"PRMs.Experimental":[102],"results":[103],"show":[104],"that":[105,130,155],"augmenting":[106],"widely-used":[107],"training":[109,145],"with":[111],"PDDL-derived":[112],"data":[113,146],"yields":[114],"substantial":[115],"improvements":[116],"both":[118],"non-mathematical":[121],"reasoning,":[122],"demonstrated":[124],"multiple":[126],"benchmarks.These":[127],"findings":[128],"indicate":[129],"constitute":[133],"effective":[137],"resource":[138],"generating":[140],"robust,":[141],"precise,":[142],"fine-grained":[144],"PRMs,":[148],"going":[149],"beyond":[150],"classical":[152],"sources":[154],"dominate":[156],"field.":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}