{"id":"https://openalex.org/W7105692598","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227916","title":"Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing","display_name":"Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105692598","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227916"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Boyuan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boyuan Chen","raw_affiliation_strings":["New York University,Tandon School of Engineering,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mingzhi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingzhi Zhu","raw_affiliation_strings":["New York University,Tandon School of Engineering,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Brendan Dolan-Gavitt","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brendan Dolan-Gavitt","raw_affiliation_strings":["New York University,Tandon School of Engineering,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Muhammad Shafique","orcid":null},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Muhammad Shafique","raw_affiliation_strings":["New York University Abu Dhabi,eBRAIN Lab, Division of Engineering,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University Abu Dhabi,eBRAIN Lab, Division of Engineering,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"last","author":{"id":null,"display_name":"Siddharth Garg","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Garg","raw_affiliation_strings":["New York University,Tandon School of Engineering,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2703,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83451873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.31459999084472656,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.31459999084472656,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.13030000030994415,"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/T10260","display_name":"Software Engineering Research","score":0.11159999668598175,"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/code","display_name":"Code (set theory)","score":0.6194000244140625},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5827999711036682},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.39750000834465027},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.3880000114440918},{"id":"https://openalex.org/keywords/test-case","display_name":"Test case","score":0.3725000023841858},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.35920000076293945},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.34119999408721924},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.3400999903678894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7942000031471252},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6194000244140625},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5827999711036682},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.3725000023841858},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.32600000500679016},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C119323957","wikidata":"https://www.wikidata.org/wiki/Q5048226","display_name":"Cascading failure","level":4,"score":0.31130000948905945},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.28450000286102295},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2651999890804291},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C53942775","wikidata":"https://www.wikidata.org/wiki/Q1211721","display_name":"Code coverage","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.25760000944137573},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C187303228","wikidata":"https://www.wikidata.org/wiki/Q867330","display_name":"Cyclomatic complexity","level":3,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319918","display_name":"York University","ror":"https://ror.org/05fq50484"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2096045964","https://openalex.org/W2979826702","https://openalex.org/W4390189088","https://openalex.org/W4402670335","https://openalex.org/W4404782125","https://openalex.org/W4404782360","https://openalex.org/W4404782516","https://openalex.org/W4404782805","https://openalex.org/W4404783393","https://openalex.org/W4404918643","https://openalex.org/W4412887834"],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,154,180,227],"large":[4],"language":[5,203],"models":[6,29,146],"(LLMs)":[7],"has":[8],"significantly":[9,36],"improved":[10],"code":[11,105,236],"completion":[12],"tasks,":[13],"yet":[14],"the":[15,46,60,65,68,100,152,187,220,231],"trade-off":[16,233],"between":[17],"accuracy":[18,115,200],"and":[19,30,72,89,116,147,158,182,194,210],"computational":[20,43],"cost":[21],"remains":[22],"a":[23,56,83,122,137,148,225],"critical":[24],"challenge.":[25],"While":[26],"using":[27],"larger":[28,145],"incorporating":[31],"inference-time":[32,90,124],"self-testing":[33,97,213],"algorithms":[34,92],"can":[35],"improve":[37],"output":[38],"accuracy,":[39],"they":[40],"incur":[41],"substantial":[42],"expenses":[44],"at":[45],"same":[47],"time.":[48],"Furthermore,":[49],"servers":[50],"in":[51,103,186,201,234],"real-world":[52],"scenarios":[53],"usually":[54],"have":[55],"dynamic":[57],"preference":[58],"on":[59,64,99,165],"cost-accuracy":[61,101,232],"tradeoff,":[62],"depending":[63],"budget,":[66],"bandwidth,":[67],"concurrent":[69],"user":[70],"volume,":[71],"users\u2019":[73],"sensitivity":[74],"to":[75,93,112,130,140,143,150,184,207,223],"wrong":[76],"answers.":[77],"In":[78],"this":[79,218],"work,":[80],"we":[81],"introduce":[82],"novel":[84],"framework":[85],"combining":[86],"model":[87,118,132,192],"cascading":[88,119,173],"self-feedback":[91],"find":[94],"multiple":[95],"near-optimal":[96],"options":[98],"tradeoff":[102],"LLM-based":[104],"generation.":[106],"Our":[107],"approach":[108,174],"leverages":[109],"self-generated":[110],"tests":[111],"both":[113,208],"enhance":[114],"evaluate":[117],"decisions.":[120],"As":[121],"blackbox":[123],"method,":[125],"it":[126],"requires":[127],"no":[128],"access":[129],"internal":[131],"parameters.":[133],"We":[134],"further":[135],"propose":[136],"threshold-based":[138],"algorithm":[139],"determine":[141],"when":[142],"deploy":[144],"heuristic":[149],"optimize":[151],"number":[153],"solutions,":[155],"test":[156,159],"cases,":[157],"lines":[160],"generated":[161],"per":[162],"model,":[163],"based":[164],"budget":[166],"constraints.":[167],"Experimental":[168],"results":[169],"show":[170],"that":[171],"our":[172,216],"reduces":[175],"costs":[176],"by":[177],"an":[178],"average":[179],"26%,":[181],"up":[183],"70%":[185],"best":[188],"case,":[189],"across":[190],"various":[191],"families":[193],"datasets,":[195],"while":[196],"maintaining":[197],"or":[198],"improving":[199],"natural":[202],"generation":[204,237],"tasks":[205],"compared":[206],"random":[209],"optimal":[211],"single-model":[212],"schemes.":[214],"To":[215],"knowledge,":[217],"is":[219],"first":[221],"work":[222],"provide":[224],"series":[226],"choices":[228],"for":[229],"optimizing":[230],"LLM":[235],"with":[238],"self-testing.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-14T00:00:00"}