{"id":"https://openalex.org/W7161574483","doi":"https://doi.org/10.1145/3802105","title":"Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards","display_name":"Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7161574483","doi":"https://doi.org/10.1145/3802105"},"language":"en","primary_location":{"id":"doi:10.1145/3802105","doi":"https://doi.org/10.1145/3802105","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3802105","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Management of Data","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3802105","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136149016","display_name":"Yuxin Zhang","orcid":"https://orcid.org/0009-0000-9475-3254","observed_orcids":["https://orcid.org/0009-0000-9475-3254","https://orcid.org/0009-0004-3083-1101"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Zhang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-3083-1101","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077800748","display_name":"Meihao Fan","orcid":"https://orcid.org/0000-0001-7597-5599","observed_orcids":["https://orcid.org/0000-0001-7597-5599"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meihao Fan","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7597-5599","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124408323","display_name":"Ju Fan","orcid":"https://orcid.org/0000-0003-4729-9903","observed_orcids":["https://orcid.org/0000-0003-4729-9903"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Fan","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4729-9903","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087695030","display_name":"Mingyang Yi","orcid":"https://orcid.org/0000-0002-2569-3849","observed_orcids":["https://orcid.org/0000-0002-2569-3849","https://orcid.org/0009-0005-2336-0687"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Yi","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-2336-0687","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614732","display_name":"Yuyu Luo","orcid":"https://orcid.org/0000-0001-9530-3327","observed_orcids":["https://orcid.org/0000-0001-9530-3327"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyu Luo","raw_affiliation_strings":["HKUST (GZ), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9530-3327","affiliations":[{"raw_affiliation_string":"HKUST (GZ), Guangzhou, China","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058334067","display_name":"G Li","orcid":"https://orcid.org/0000-0002-1398-0621","observed_orcids":["https://orcid.org/0000-0002-1398-0621","https://orcid.org/0000-0001-9755-2781","https://orcid.org/0000-0002-2179-8555"]},"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":"Guoliang Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1398-0621","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047062688","display_name":"Bin Wu","orcid":"https://orcid.org/0000-0002-4743-1006","observed_orcids":["https://orcid.org/0000-0002-4743-1006"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wu","raw_affiliation_strings":["Alibaba Cloud Computing, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4743-1006","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136449805","display_name":"Wenchao Zhou","orcid":"https://orcid.org/0009-0002-2689-6020","observed_orcids":["https://orcid.org/0009-0002-2689-6020"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenchao Zhou","raw_affiliation_strings":["Alibaba Cloud Computing, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-2689-6020","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.1934,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.97293062,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"4","issue":"3","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.4611999988555908,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.4611999988555908,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10028","display_name":"Topic Modeling","score":0.18299999833106995,"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":0.11320000141859055,"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/text-to-sql","display_name":"text-to-SQL","score":0.9800000190734863},{"id":"https://openalex.org/keywords/process-reward-models","display_name":"process reward models","score":0.8610000014305115},{"id":"https://openalex.org/keywords/common-table-expressions","display_name":"common table expressions","score":0.7129999995231628},{"id":"https://openalex.org/keywords/reinforcement-learning-from-human-feedback","display_name":"reinforcement learning from human feedback","score":0.6389999985694885},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7450000047683716},{"id":"https://openalex.org/keywords/database-query-generation","display_name":"database query generation","score":0.5270000100135803},{"id":"https://openalex.org/keywords/domain-generalization","display_name":"domain generalization","score":0.8479999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544000148773193},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7038999795913696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6883999705314636},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5579000115394592},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5042999982833862},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.39590001106262207},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.36980000138282776},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C3746660","wikidata":"https://www.wikidata.org/wiki/Q1068763","display_name":"Rule of inference","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3802105","doi":"https://doi.org/10.1145/3802105","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3802105","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Management of Data","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2505.04671","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.04671","pdf_url":"https://arxiv.org/pdf/2505.04671","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.2505.04671","doi":"https://doi.org/10.48550/arxiv.2505.04671","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.04671","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3802105","doi":"https://doi.org/10.1145/3802105","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3802105","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G358029826","display_name":null,"funder_award_id":"62436010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4675535004","display_name":null,"funder_award_id":"62402409","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5725260554","display_name":null,"funder_award_id":"62232009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7226997889","display_name":null,"funder_award_id":"62441230","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7401710730","display_name":null,"funder_award_id":"62525202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316125","display_name":"China Railway","ror":"https://ror.org/044wv3489"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W3087592560","https://openalex.org/W4381326864","https://openalex.org/W4396571402","https://openalex.org/W4399175046","https://openalex.org/W4400909484","https://openalex.org/W4402043038","https://openalex.org/W4412623423","https://openalex.org/W4412877147","https://openalex.org/W4412888553","https://openalex.org/W4414243417","https://openalex.org/W4417302266","https://openalex.org/W7133205963"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,34,141],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"trained":[7],"with":[8,21,92,101,160,188,198],"reinforcement":[9],"learning":[10],"(RL)":[11],"have":[12],"improved":[13],"Text-to-SQL":[14],"performance.":[15],"However,":[16],"RL-based":[17],"approaches":[18],"still":[19],"struggle":[20],"complex":[22],"queries":[23,64],"due":[24],"to":[25],"two":[26],"key":[27],"limitations:":[28],"insufficient":[29],"stepwise":[30],"execution-aware":[31,57,113,157],"reasoning":[32,45,58,84,104,170],"grounded":[33],"database":[35],"feedback,":[36],"and":[37,56,69,78,115,119,127,143,166,179,184,202],"the":[38,129,138,145],"lack":[39],"of":[40],"process-level":[41,189],"rewards":[42,124],"for":[43],"guiding":[44],"optimization.":[46],"To":[47,80],"address":[48],"these":[49],"issues,":[50],"we":[51,86],"propose":[52],"CoCTE,":[53],"a":[54,82,89,150],"divide-and-conquer":[55],"framework":[59],"that":[60,155,193],"progressively":[61],"composes":[62],"SQL":[63],"through":[65],"intermediate":[66],"view":[67],"validation":[68],"structured":[70,102],"Common":[71],"Table":[72],"Expressions":[73],"(CTEs),":[74],"improving":[75,185],"both":[76,176],"accuracy":[77],"interpretability.":[79],"realize":[81],"CoCTE":[83,103],"process,":[85],"develop":[87],"Reward-SQL,":[88],"unified":[90],"approach":[91],"three":[93],"stages:":[94],"(1)":[95],"model":[96,153,200],"initialization,":[97],"which":[98,110,121],"equips":[99],"LLMs":[100],"capabilities;":[105],"(2)":[106],"process":[107,123,133,151],"reward":[108,152],"design,":[109],"delivers":[111],"fine-grained,":[112],"supervision;":[114],"(3)":[116],"process-supervised":[117],"RL":[118,177],"inference,":[120],"integrates":[122],"into":[125,175],"training":[126,178],"guides":[128],"inference":[130,180],"stage":[131],"by":[132],"rewards.":[134],"This":[135],"paper":[136],"addresses":[137],"core":[139],"challenges":[140],"Reward-SQL":[142,194],"makes":[144],"following":[146],"contributions.":[147],"We":[148,172],"introduce":[149],"(PRM)":[154],"combines":[156],"trajectory":[158,186],"scoring":[159],"entropy-based":[161],"step":[162],"weighting,":[163],"providing":[164],"dense":[165],"interpretable":[167],"supervision":[168],"across":[169],"steps.":[171],"integrate":[173],"PRM":[174],"stages,":[181],"stabilizing":[182],"optimization":[183],"exploration":[187],"signals.":[190],"Experiments":[191],"show":[192],"significantly":[195],"outperforms":[196],"baselines":[197],"comparable":[199],"sizes,":[201],"exhibits":[203],"strong":[204],"cross-domain":[205],"generalization.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2026-05-19T00:00:00"}