{"id":"https://openalex.org/W7115887377","doi":"https://doi.org/10.1007/s44311-025-00034-4","title":"Specializing large language models for process modeling via reinforcement learning with verifiable and universal rewards","display_name":"Specializing large language models for process modeling via reinforcement learning with verifiable and universal rewards","publication_year":2025,"publication_date":"2025-12-18","ids":{"openalex":"https://openalex.org/W7115887377","doi":"https://doi.org/10.1007/s44311-025-00034-4"},"language":"en","primary_location":{"id":"doi:10.1007/s44311-025-00034-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44311-025-00034-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44311-025-00034-4.pdf","source":{"id":"https://openalex.org/S5407036648","display_name":"Process Science","issn_l":"2948-2178","issn":["2948-2178"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Process Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s44311-025-00034-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Alessandro Berti","orcid":"https://orcid.org/0000-0002-3279-4795"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alessandro Berti","raw_affiliation_strings":["RWTH Aachen University, Ahornstra\u00dfe 55, 52074, Aachen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3279-4795","affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Ahornstra\u00dfe 55, 52074, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoting Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xiaoting Wang","raw_affiliation_strings":["RWTH Aachen University, Ahornstra\u00dfe 55, 52074, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Ahornstra\u00dfe 55, 52074, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Humam Kourani","orcid":"https://orcid.org/0000-0003-2375-2152"},"institutions":[{"id":"https://openalex.org/I4210110507","display_name":"Fraunhofer Institute for Applied Information Technology","ror":"https://ror.org/01ak24c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210110507","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Humam Kourani","raw_affiliation_strings":["Fraunhofer Institute for Applied Information Technology FIT, Schloss Birlinghoven, 53757, Sankt Augustin, Germany","RWTH Aachen University, Ahornstra\u00dfe 55, 52074, Aachen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2375-2152","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Applied Information Technology FIT, Schloss Birlinghoven, 53757, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210110507"]},{"raw_affiliation_string":"RWTH Aachen University, Ahornstra\u00dfe 55, 52074, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wil M. P. Van der Aalst","orcid":"https://orcid.org/0000-0002-0955-6940"},"institutions":[{"id":"https://openalex.org/I4210110507","display_name":"Fraunhofer Institute for Applied Information Technology","ror":"https://ror.org/01ak24c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210110507","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wil M. P. Van der Aalst","raw_affiliation_strings":["Fraunhofer Institute for Applied Information Technology FIT, Schloss Birlinghoven, 53757, Sankt Augustin, Germany","RWTH Aachen University, Ahornstra\u00dfe 55, 52074, Aachen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0955-6940","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Applied Information Technology FIT, Schloss Birlinghoven, 53757, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210110507"]},{"raw_affiliation_string":"RWTH Aachen University, Ahornstra\u00dfe 55, 52074, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66220246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.9401000142097473,"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":0.9401000142097473,"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/T13287","display_name":"Robotic Process Automation Applications","score":0.004800000227987766,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.003000000026077032,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6606000065803528},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.6370000243186951},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6018999814987183},{"id":"https://openalex.org/keywords/process-modeling","display_name":"Process modeling","score":0.5090000033378601},{"id":"https://openalex.org/keywords/modeling-language","display_name":"Modeling language","score":0.4399000108242035},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43959999084472656},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.38530001044273376},{"id":"https://openalex.org/keywords/petri-net","display_name":"Petri net","score":0.3833000063896179},{"id":"https://openalex.org/keywords/business-process-modeling","display_name":"Business process modeling","score":0.367000013589859},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.361299991607666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8136000037193298},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6606000065803528},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6370000243186951},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246000289916992},{"id":"https://openalex.org/C76956256","wikidata":"https://www.wikidata.org/wiki/Q27610560","display_name":"Process modeling","level":3,"score":0.5090000033378601},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.4399000108242035},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.41100001335144043},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C38677869","wikidata":"https://www.wikidata.org/wiki/Q724168","display_name":"Petri net","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.375},{"id":"https://openalex.org/C207505557","wikidata":"https://www.wikidata.org/wiki/Q4374012","display_name":"Business process modeling","level":4,"score":0.367000013589859},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35089999437332153},{"id":"https://openalex.org/C2775948798","wikidata":"https://www.wikidata.org/wiki/Q5160261","display_name":"Conformance checking","level":5,"score":0.3402999937534332},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C92548554","wikidata":"https://www.wikidata.org/wiki/Q2262868","display_name":"Domain model","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3156000077724457},{"id":"https://openalex.org/C85345410","wikidata":"https://www.wikidata.org/wiki/Q851587","display_name":"Business process","level":3,"score":0.31369999051094055},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C124670913","wikidata":"https://www.wikidata.org/wiki/Q2608526","display_name":"Process mining","level":5,"score":0.2815999984741211},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2780330621","wikidata":"https://www.wikidata.org/wiki/Q7936609","display_name":"Visual modeling","level":4,"score":0.26910001039505005},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C78639753","wikidata":"https://www.wikidata.org/wiki/Q3318160","display_name":"Behavioral modeling","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C111065885","wikidata":"https://www.wikidata.org/wiki/Q1189053","display_name":"Fuzz testing","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2551000118255615},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44311-025-00034-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44311-025-00034-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44311-025-00034-4.pdf","source":{"id":"https://openalex.org/S5407036648","display_name":"Process Science","issn_l":"2948-2178","issn":["2948-2178"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Process Science","raw_type":"journal-article"},{"id":"pmh:oai:econstor.eu:10419/335082","is_oa":true,"landing_page_url":"https://hdl.handle.net/10419/335082","pdf_url":null,"source":{"id":"https://openalex.org/S4306401696","display_name":"Econstor (Econstor)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:article"}],"best_oa_location":{"id":"doi:10.1007/s44311-025-00034-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44311-025-00034-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44311-025-00034-4.pdf","source":{"id":"https://openalex.org/S5407036648","display_name":"Process Science","issn_l":"2948-2178","issn":["2948-2178"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Process Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.5749304890632629,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320324232","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7115887377.pdf","grobid_xml":"https://content.openalex.org/works/W7115887377.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W4323980634","https://openalex.org/W4385555616","https://openalex.org/W4385605699","https://openalex.org/W4404635561","https://openalex.org/W4404701973","https://openalex.org/W4407111066","https://openalex.org/W4407175928","https://openalex.org/W4413906832"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Process":[1],"models":[2,23,64,130,218,256],"are":[3],"central":[4],"artefacts":[5],"in":[6,29,101],"business":[7],"process":[8,63,98,109,118,139,164,182,213],"management:":[9],"they":[10],"drive":[11],"analysis,":[12],"automation,":[13],"simulation,":[14],"and":[15,20,26,33,58,79,90,133,142,196,223,237],"compliance":[16],"checking.":[17],"Yet":[18],"creating":[19],"maintaining":[21],"high-quality":[22],"is":[24],"labor-intensive":[25],"requires":[27],"expertise":[28],"both":[30,127],"the":[31,43,111,244,247,251],"domain":[32],"formal":[34,62],"notations":[35],"such":[36,66,86],"as":[37,87,134],"Petri":[38],"nets":[39],"or":[40,161],"BPMN.":[41],"At":[42],"same":[44],"time,":[45],"many":[46],"organisations":[47],"already":[48],"document":[49],"their":[50],"processes":[51],"informally":[52],"through":[53],"textual":[54,108,212],"work":[55],"instructions,":[56],"guidelines,":[57],"tickets.":[59],"Automatically":[60],"generating":[61],"from":[65,131],"natural-language":[67],"descriptions":[68,214],"would":[69],"therefore":[70],"accelerate":[71],"modeling,":[72],"keep":[73],"model":[74,99,112,143,183,232,241],"repositories":[75],"aligned":[76],"with":[77,155,199,215],"documentation,":[78],"provide":[80],"stronger":[81],"support":[82,220],"for":[83,138,181],"downstream":[84],"uses":[85],"conformance":[88],"checking":[89],"digital":[91],"twins.":[92],"In":[93],"this":[94,156,168],"work,":[95],"we":[96,170],"study":[97],"generation":[100],"a":[102,107,115,135,177,208],"narrow,":[103],"technical":[104],"sense:":[105],"given":[106],"description,":[110],"must":[113],"produce":[114],"complete,":[116],"executable":[117],"model.":[119],"This":[120],"generative":[121],"capability":[122],"can":[123],"then":[124],"be":[125],"used":[126],"to":[128,175,219],"propose":[129],"scratch":[132],"building":[136],"block":[137],"modeling":[140],"assistance":[141],"completion.":[144],"Large":[145],"Language":[146],"Models":[147],"(LLMs)":[148],"pretrained":[149,178],"on":[150,193],"generic":[151],"text":[152],"often":[153],"struggle":[154],"task,":[157],"producing":[158,258],"syntactically":[159],"invalid":[160,231,260],"behaviorally":[162],"incorrect":[163],"models.":[165],"To":[166],"address":[167],"limitation,":[169],"apply":[171],"Reinforcement":[172],"Learning":[173],"(RL)":[174],"specialize":[176],"LLM":[179],"specifically":[180],"generation.":[184],"Our":[185],"RL":[186,228],"approach":[187],"combines":[188],"automatically":[189],"verifiable":[190],"rewards,":[191],"based":[192],"structural":[194],"checks":[195],"behavioral":[197,235],"footprints,":[198],"universal":[200],"judgments":[201],"provided":[202],"by":[203],"an":[204],"LLM-as-a-Judge.":[205],"We":[206],"created":[207],"dataset":[209],"of":[210,253],"1312":[211],"corresponding":[216],"reference":[217],"Supervised":[221],"Fine-Tuning":[222],"RL.":[224],"Experiments":[225],"demonstrate":[226],"that":[227],"significantly":[229],"reduces":[230],"generations,":[233],"improves":[234],"correctness,":[236],"allows":[238],"control":[239],"over":[240],"complexity.":[242],"On":[243],"ProMoAI":[245],"benchmark,":[246],"resulting":[248],"checkpoint":[249],"approaches":[250],"performance":[252],"state-of-the-art":[254],"proprietary":[255],"while":[257],"fewer":[259],"generations.":[261]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-12-19T00:00:00"}