{"id":"https://openalex.org/W4407123926","doi":"https://doi.org/10.48550/arxiv.2502.00675","title":"ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration","display_name":"ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration","publication_year":2025,"publication_date":"2025-02-02","ids":{"openalex":"https://openalex.org/W4407123926","doi":"https://doi.org/10.48550/arxiv.2502.00675"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.00675","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.00675","pdf_url":"https://arxiv.org/pdf/2502.00675","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.00675","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Deng, Minghang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deng, Minghang","raw_affiliation_strings":["University of California , San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115000219","display_name":"Ashwin Ramachandran","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramachandran, Ashwin","raw_affiliation_strings":["University of California , San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102941860","display_name":"Canwen Xu","orcid":"https://orcid.org/0000-0002-1552-999X","observed_orcids":["https://orcid.org/0000-0002-1552-999X"]},"institutions":[{"id":"https://openalex.org/I4400600931","display_name":"Snowflake Inc. (United States)","ror":"https://ror.org/04vrpfw15","country_code":"US","type":"company","lineage":["https://openalex.org/I4400600931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Canwen","raw_affiliation_strings":["Snowflake AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snowflake AI Research","institution_ids":["https://openalex.org/I4400600931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111055876","display_name":"Lanxiang Hu","orcid":"https://orcid.org/0000-0003-0641-3677","observed_orcids":["https://orcid.org/0000-0003-0641-3677"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I4400600931","display_name":"Snowflake Inc. (United States)","ror":"https://ror.org/04vrpfw15","country_code":"US","type":"company","lineage":["https://openalex.org/I4400600931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hu, Lanxiang","raw_affiliation_strings":["Snowflake AI Research","University of California , San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snowflake AI Research","institution_ids":["https://openalex.org/I4400600931"]},{"raw_affiliation_string":"University of California , San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102915910","display_name":"Zhewei Yao","orcid":"https://orcid.org/0000-0001-7678-4321","observed_orcids":["https://orcid.org/0000-0001-7678-4321"]},"institutions":[{"id":"https://openalex.org/I4400600931","display_name":"Snowflake Inc. (United States)","ror":"https://ror.org/04vrpfw15","country_code":"US","type":"company","lineage":["https://openalex.org/I4400600931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yao, Zhewei","raw_affiliation_strings":["Snowflake AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snowflake AI Research","institution_ids":["https://openalex.org/I4400600931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111177928","display_name":"Anupam Datta","orcid":"https://orcid.org/0000-0002-2751-068X","observed_orcids":["https://orcid.org/0000-0002-2751-068X"]},"institutions":[{"id":"https://openalex.org/I4400600931","display_name":"Snowflake Inc. (United States)","ror":"https://ror.org/04vrpfw15","country_code":"US","type":"company","lineage":["https://openalex.org/I4400600931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Datta, Anupam","raw_affiliation_strings":["Snowflake AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snowflake AI Research","institution_ids":["https://openalex.org/I4400600931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396851","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-0896-4555","observed_orcids":["https://orcid.org/0000-0002-0896-4555"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I4400600931","display_name":"Snowflake Inc. (United States)","ror":"https://ror.org/04vrpfw15","country_code":"US","type":"company","lineage":["https://openalex.org/I4400600931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Hao","raw_affiliation_strings":["Snowflake AI Research","University of California , San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snowflake AI Research","institution_ids":["https://openalex.org/I4400600931"]},{"raw_affiliation_string":"University of California , San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":58,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.3463999927043915,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.3463999927043915,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.2434999942779541,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.23000000417232513,"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":0.9070000052452087},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7409999966621399},{"id":"https://openalex.org/keywords/self-refinement","display_name":"self-refinement","score":0.9440000057220459},{"id":"https://openalex.org/keywords/sql-dialects","display_name":"SQL dialects","score":0.7160000205039978},{"id":"https://openalex.org/keywords/execution-feedback","display_name":"execution feedback","score":0.7110000252723694},{"id":"https://openalex.org/keywords/spider-benchmark","display_name":"Spider benchmark","score":0.5789999961853027}],"concepts":[{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.8347175121307373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6665353775024414},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6474301815032959},{"id":"https://openalex.org/C167544706","wikidata":"https://www.wikidata.org/wiki/Q360842","display_name":"SQL/PSM","level":5,"score":0.4729078710079193},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4489879608154297},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36250054836273193},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32820260524749756},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.19542726874351501},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.1897580623626709},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.04770633578300476},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.00675","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.00675","pdf_url":"https://arxiv.org/pdf/2502.00675","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.2502.00675","doi":"https://doi.org/10.48550/arxiv.2502.00675","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.00675","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.00675","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.00675","pdf_url":"https://arxiv.org/pdf/2502.00675","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407123926.pdf","grobid_xml":"https://content.openalex.org/works/W4407123926.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2952380375","https://openalex.org/W2985377636","https://openalex.org/W3200285169","https://openalex.org/W4221161695","https://openalex.org/W4304195432","https://openalex.org/W4327810158","https://openalex.org/W4365205411","https://openalex.org/W4385570088","https://openalex.org/W4385965642","https://openalex.org/W4385968025","https://openalex.org/W4389518686","https://openalex.org/W4389519829","https://openalex.org/W4389524074","https://openalex.org/W4391631327","https://openalex.org/W4396571402","https://openalex.org/W4399115971","https://openalex.org/W4399175046","https://openalex.org/W4399401005","https://openalex.org/W4402502803","https://openalex.org/W4403854021","https://openalex.org/W4404406411","https://openalex.org/W4405025318","https://openalex.org/W4405655184","https://openalex.org/W4411403530","https://openalex.org/W4411449940","https://openalex.org/W4413978227","https://openalex.org/W4415035611","https://openalex.org/W4417222331","https://openalex.org/W6967204841"],"related_works":["https://openalex.org/W7125783495","https://openalex.org/W7163710186","https://openalex.org/W7130689383","https://openalex.org/W7152595661","https://openalex.org/W7125503848","https://openalex.org/W7160244468","https://openalex.org/W4417529659","https://openalex.org/W7168183441","https://openalex.org/W7168152732","https://openalex.org/W4416684447"],"abstract_inverted_index":{"We":[0],"present":[1],"ReFoRCE,":[2],"a":[3],"Text-to-SQL":[4,17,20],"agent":[5],"that":[6],"tops":[7],"the":[8],"Spider":[9,130,135],"2.0":[10],"leaderboard--a":[11],"challenging":[12],"benchmark":[13],"reflecting":[14],"complex,":[15],"real-world":[16],"scenarios.":[18],"While":[19],"systems":[21],"enable":[22],"natural":[23],"language":[24],"queries":[25],"over":[26,42],"structured":[27],"databases,":[28],"deploying":[29],"them":[30],"in":[31],"enterprise":[32],"environments":[33],"remains":[34],"difficult":[35],"due":[36],"to":[37,76,82,94,115],"large,":[38],"complex":[39],"schemas":[40],"(with":[41],"1,000":[43],"columns),":[44],"diverse":[45],"SQL":[46],"dialects":[47],"(e.g.,":[48,55],"BigQuery,":[49],"Snowflake),":[50],"and":[51,57,72,86,106,132],"sophisticated":[52,104],"query":[53],"requirements":[54],"transformations":[56],"analytics).":[58],"ReFoRCE":[59,120],"addresses":[60],"these":[61],"challenges":[62],"through:":[63],"(a)":[64],"database":[65],"information":[66],"compression":[67],"via":[68],"pattern-based":[69],"table":[70],"grouping":[71],"LLM-guided":[73],"schema":[74],"linking":[75],"alleviate":[77],"long-context":[78],"issues;":[79],"(b)":[80],"self-refinement":[81],"iteratively":[83],"correct":[84],"syntax":[85],"semantic":[87],"errors":[88],"across":[89],"dialects;":[90],"(c)":[91],"majority-vote":[92],"consensus":[93],"select":[95],"high-confidence":[96],"candidates":[97],"while":[98],"deferring":[99],"ambiguous":[100],"cases":[101],"arising":[102],"from":[103],"queries;":[105],"(d)":[107],"iterative":[108],"column":[109],"exploration":[110],"guided":[111],"by":[112],"execution":[113],"feedback":[114],"resolve":[116],"those":[117],"deferred":[118],"cases.":[119],"achieves":[121],"new":[122],"state-of-the-art":[123],"results,":[124],"with":[125],"scores":[126],"of":[127],"35.83":[128],"on":[129,134],"2.0-Snow":[131],"36.56":[133],"2.0-Lite.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":44},{"year":2025,"cited_by_count":14}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-02-05T00:00:00"}