{"id":"https://openalex.org/W7204159978","doi":"https://doi.org/10.21203/rs.3.rs-10798738/v1","title":"Self-Optimizing Enterprise RAG+SQL Knowledge Agents: Unified Retrieval, Schema-Aware Query Translation, Event Graph Reasoning, and Adaptive Model Routing","display_name":"Self-Optimizing Enterprise RAG+SQL Knowledge Agents: Unified Retrieval, Schema-Aware Query Translation, Event Graph Reasoning, and Adaptive Model Routing","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204159978","doi":"https://doi.org/10.21203/rs.3.rs-10798738/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-10798738/v1","doi":"https://doi.org/10.21203/rs.3.rs-10798738/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10798738/v1","pdf_url":"https://www.researchsquare.com/article/rs-10798738/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-10798738/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143444377","display_name":"Harshil Lodhiya","orcid":"https://orcid.org/0009-0005-5798-9176","observed_orcids":["https://orcid.org/0009-0005-5798-9176"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Harshil Lodhiya","raw_affiliation_strings":["SlicedHealth, Inc"],"raw_orcid":"https://orcid.org/0009-0005-5798-9176","affiliations":[{"raw_affiliation_string":"SlicedHealth, Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5143444377"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T10028","display_name":"Topic Modeling","score":0.6273999810218811,"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/T10028","display_name":"Topic Modeling","score":0.6273999810218811,"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":0.2655999958515167,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.03139999881386757,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9449999928474426},{"id":"https://openalex.org/keywords/text-to-sql","display_name":"text-to-SQL","score":0.9819999933242798},{"id":"https://openalex.org/keywords/knowledge-graphs","display_name":"knowledge graphs","score":0.5709999799728394},{"id":"https://openalex.org/keywords/event-graphs","display_name":"event graphs","score":0.5649999976158142},{"id":"https://openalex.org/keywords/feedback-control","display_name":"feedback control","score":0.5569999814033508},{"id":"https://openalex.org/keywords/self-optimizing-control","display_name":"self-optimizing control","score":0.6610000133514404},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926999926567078},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.48750001192092896},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C27295321","wikidata":"https://www.wikidata.org/wiki/Q831795","display_name":"Enterprise information system","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C2778744189","wikidata":"https://www.wikidata.org/wiki/Q4677551","display_name":"Active database","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C180591056","wikidata":"https://www.wikidata.org/wiki/Q654437","display_name":"Executor","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26420000195503235},{"id":"https://openalex.org/C123606473","wikidata":"https://www.wikidata.org/wiki/Q907918","display_name":"Complex event processing","level":3,"score":0.25929999351501465},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C138824270","wikidata":"https://www.wikidata.org/wiki/Q3318162","display_name":"Enterprise modelling","level":4,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-10798738/v1","doi":"https://doi.org/10.21203/rs.3.rs-10798738/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10798738/v1","pdf_url":"https://www.researchsquare.com/article/rs-10798738/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-10798738/v1","doi":"https://doi.org/10.21203/rs.3.rs-10798738/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10798738/v1","pdf_url":"https://www.researchsquare.com/article/rs-10798738/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204159978.pdf","grobid_xml":"https://content.openalex.org/works/W7204159978.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7154069087","https://openalex.org/W7163925796","https://openalex.org/W7165074245","https://openalex.org/W7160601368","https://openalex.org/W7161375790","https://openalex.org/W7128471263","https://openalex.org/W4411120010","https://openalex.org/W7129712200","https://openalex.org/W7141055573","https://openalex.org/W7221438024"],"abstract_inverted_index":{"Abstract":[0],"Enterprise":[1,96],"knowledge":[2,111],"is":[3,208],"fragmented":[4],"across":[5],"relational":[6,137],"databases,":[7,33],"PDFs,":[8],"incident":[9,83],"reports,":[10],"tickets,":[11],"logs,":[12],"spreadsheets,":[13],"policy":[14,65],"documents,":[15],"and":[16,55,67,84,115,133,152,156,164,184,202],"operational":[17],"runbooks.":[18],"Retrieval-augmented":[19],"generation":[20],"(RAG)":[21],"systems":[22,29],"help":[23,30],"with":[24,31],"unstructured":[25],"text,":[26],"while":[27],"text-to-SQL":[28],"structured":[32],"but":[34],"production":[35],"workflows":[36],"frequently":[37],"require":[38],"both":[39],"forms":[40],"of":[41],"reasoning":[42],"in":[43,145],"the":[44,68,78,85,94],"same":[45],"answer.":[46],"A":[47],"finance":[48],"analyst":[49],"may":[50,61,75],"ask":[51,62,76],"for":[52,63,77],"contract":[53],"terms":[54],"revenue":[56],"aggregates;":[57],"a":[58,64,72,100,189,217,226],"compliance":[59],"officer":[60],"exception":[66],"exact":[69],"affected":[70],"accounts;":[71],"support":[73],"lead":[74],"causal":[79],"sequence":[80],"behind":[81],"an":[82],"customer":[86],"records":[87],"touched":[88],"by":[89],"it.":[90],"This":[91],"paper":[92],"introduces":[93],"Self-Optimizing":[95],"RAG+SQL":[97],"Knowledge":[98],"Agent,":[99],"middleware":[101],"architecture":[102],"that":[103,209],"unifies":[104],"schema-aware":[105,173],"SQL":[106,144],"translation,":[107,175],"document":[108],"retrieval,":[109],"event-schema":[110],"graphs,":[112,142],"execution":[113],"validation,":[114],"adaptive":[116],"model":[117,182],"routing.":[118],"The":[119,167,205],"proposed":[120],"agent":[121],"decomposes":[122],"enterprise":[123,210],"questions":[124],"into":[125],"typed":[126],"evidence":[127],"plans,":[128],"retrieves":[129],"from":[130,159],"hybrid":[131,177],"vector":[132],"graph":[134],"indexes,":[135],"prunes":[136],"schemas":[138],"through":[139],"schema":[140],"relationship":[141],"executes":[143],"bounded":[146],"read-only":[147],"sandboxes,":[148],"composes":[149],"multi-source":[150],"evidence,":[151],"continuously":[153],"up-dates":[154],"routing":[155,194],"retrieval":[157],"policies":[158],"observed":[160],"quality,":[161],"latency,":[162],"cost,":[163],"validation":[165,196],"feedback.":[166],"design":[168],"extends":[169],"prior":[170],"work":[171],"on":[172],"query":[174],"EventForge":[176],"RAG+KG":[178],"storage,":[179],"LLM-Advisor":[180],"dynamic":[181],"routing,":[183],"feedback-control":[185],"allocation.":[186],"We":[187],"provide":[188],"detailed":[190],"architecture,":[191],"objective":[192],"function,":[193],"policy,":[195],"protocol,":[197],"benchmark":[198],"design,":[199],"implementation":[200],"blueprint,":[201],"risk":[203],"analysis.":[204],"central":[206],"claim":[207],"question":[211],"answering":[212],"should":[213],"be":[214],"treated":[215],"as":[216,225],"self-optimizing":[218],"control":[219],"problem":[220],"over":[221,229],"heterogeneous":[222],"knowledgetools,":[223],"not":[224],"single":[227],"prompt":[228],"retrieved":[230],"text.":[231]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-08-26T00:00:00"}