{"id":"https://openalex.org/W4417070540","doi":"https://doi.org/10.1145/3769826","title":"SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer","display_name":"SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W4417070540","doi":"https://doi.org/10.1145/3769826"},"language":"en","primary_location":{"id":"doi:10.1145/3769826","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769826","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,"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"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3769826","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100757250","display_name":"Hanwen Liu","orcid":"https://orcid.org/0000-0002-5265-9312"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hanwen Liu","raw_affiliation_strings":["University of Southern California, Los Angeles, California, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110335200","display_name":"Q. Zhang","orcid":"https://orcid.org/0009-0005-5785-8766"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qihan Zhang","raw_affiliation_strings":["University of Southern California, Los Angeles, California, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025731013","display_name":"Ryan Marcus","orcid":"https://orcid.org/0000-0002-1279-1124"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Marcus","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, Pennsylvania, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062053667","display_name":"Ibrahim Sabek","orcid":"https://orcid.org/0009-0006-2102-5241"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ibrahim Sabek","raw_affiliation_strings":["University of Southern California, Los Angeles, California, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, California, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100757250"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46322592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"6","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":0.5874999761581421,"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":0.5874999761581421,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.2513999938964844,"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/T11106","display_name":"Data Management and Algorithms","score":0.05220000073313713,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/leverage","display_name":"Leverage (statistics)","score":0.6478000283241272},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.6026999950408936},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.508400022983551},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4553999900817871},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.44600000977516174},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.4259999990463257},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.387800008058548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8422999978065491},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6478000283241272},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.6026999950408936},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.44600000977516174},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38600000739097595},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C96956885","wikidata":"https://www.wikidata.org/wiki/Q6138701","display_name":"RDF query language","level":5,"score":0.2809999883174896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28029999136924744},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.26429998874664307}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769826","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769826","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,"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"}],"best_oa_location":{"id":"doi:10.1145/3769826","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769826","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,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2396309311","https://openalex.org/W2970148517","https://openalex.org/W3197977787","https://openalex.org/W4282550406","https://openalex.org/W4317641620","https://openalex.org/W4366492480","https://openalex.org/W4375928354","https://openalex.org/W4380433215","https://openalex.org/W4383749444","https://openalex.org/W4385569780","https://openalex.org/W4386128230","https://openalex.org/W4386768482","https://openalex.org/W4391849320","https://openalex.org/W4396571402","https://openalex.org/W4402043024","https://openalex.org/W4402671689","https://openalex.org/W4403899386","https://openalex.org/W4407039130"],"related_works":[],"abstract_inverted_index":{"Query":[0],"optimization":[1],"is":[2],"a":[3,76,103],"crucial":[4],"problem":[5,93],"in":[6,180],"database":[7],"systems":[8],"that":[9,168],"has":[10],"been":[11],"studied":[12],"for":[13,67],"decades.":[14],"Learned":[15],"query":[16,45,126,163,181],"optimizers":[17,46],"(LQOs)":[18],"can":[19],"improve":[20],"performance":[21],"over":[22],"time":[23],"by":[24,96,136],"incorporating":[25],"feedback;":[26],"however,":[27],"they":[28,57],"suffer":[29],"from":[30,99],"cold-start":[31,92],"issues":[32],"and":[33,49,62,113,124,145,177,186],"often":[34],"require":[35],"retraining":[36],"when":[37],"workloads":[38],"shift":[39],"or":[40],"schemas":[41],"change.":[42],"Recent":[43],"LLM-based":[44],"leverage":[47],"pre-trained":[48],"fine-tuned":[50],"LLMs":[51],"to":[52,116,120,142,161,175,191],"mitigate":[53],"these":[54],"challenges.":[55],"Nevertheless,":[56],"neglect":[58],"LLMs'":[59],"in-context":[60,133],"learning":[61,98,134],"execution":[63,100,148,164],"records":[64],"as":[65],"feedback":[66,101],"continuous":[68],"evolution.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"present":[74],"SEFRQO,":[75],"S":[77],"elf-":[78],"E":[79],"volving":[80],"F":[81],"ine-tuned":[82],"R":[83],"AG-based":[84],"Q":[85],"uery":[86],"O":[87],"ptimizer.":[88],"SEFRQO":[89,129,169],"mitigates":[90],"the":[91,118,131,146,151,159,184],"of":[94,150],"LQOs":[95],"continuously":[97],"via":[102],"Retrieval-Augmented":[104],"Generation":[105],"(RAG)":[106],"framework.":[107],"We":[108],"employ":[109],"both":[110],"supervised":[111],"fine-tuning":[112,115],"reinforcement":[114],"prepare":[117],"LLM":[119],"produce":[121],"syntactically":[122],"correct":[123],"performance-efficient":[125],"hints.":[127],"Moreover,":[128],"leverages":[130],"LLM's":[132],"capabilities":[135],"dynamically":[137],"constructing":[138],"prompts":[139],"with":[140],"references":[141],"similar":[143],"queries":[144],"historical":[147],"record":[149],"same":[152],"query.":[153],"This":[154],"self-evolving":[155],"paradigm":[156],"iteratively":[157],"optimizes":[158],"prompt":[160],"minimize":[162],"latency.":[165],"Evaluations":[166],"show":[167],"outperforms":[170],"state-of-the-art":[171],"LQOs,":[172],"achieving":[173],"up":[174],"65.05%":[176],"93.57%":[178],"reductions":[179],"latency":[182],"on":[183],"CEB":[185],"Stack":[187],"workloads,":[188],"respectively,":[189],"compared":[190],"PostgreSQL.":[192]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-06T00:00:00"}