{"id":"https://openalex.org/W4406866655","doi":"https://doi.org/10.1145/3714462","title":"Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation","display_name":"Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation","publication_year":2025,"publication_date":"2025-01-27","ids":{"openalex":"https://openalex.org/W4406866655","doi":"https://doi.org/10.1145/3714462"},"language":"en","primary_location":{"id":"doi:10.1145/3714462","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3714462","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"type":"article","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":"https://openalex.org/A5100329466","display_name":"Chong Wang","orcid":"https://orcid.org/0000-0003-1424-6290"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chong Wang","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-1424-6290","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035797029","display_name":"Jian Zhang","orcid":"https://orcid.org/0000-0001-8316-1894"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8316-1894","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026905803","display_name":"Yebo Feng","orcid":"https://orcid.org/0000-0002-7235-2377"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yebo Feng","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7235-2377","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674538","display_name":"Tianlin Li","orcid":"https://orcid.org/0000-0002-2207-1622"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianlin Li","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2207-1622","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013856385","display_name":"Weisong Sun","orcid":"https://orcid.org/0000-0001-9236-8264"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weisong Sun","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9236-8264","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355692","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-7300-9215"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7300-9215","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101854992","display_name":"Xin Peng","orcid":"https://orcid.org/0000-0003-3376-2581"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Peng","raw_affiliation_strings":["Fudan University, China"],"raw_orcid":"https://orcid.org/0000-0003-3376-2581","affiliations":[{"raw_affiliation_string":"Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":57.4508,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.99890752,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"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/T10260","display_name":"Software Engineering Research","score":0.9854000210762024,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9854000210762024,"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/T13999","display_name":"Digital Rights Management and Security","score":0.9747999906539917,"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/T13681","display_name":"Engineering and Information Technology","score":0.9702000021934509,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7288544178009033},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5469260215759277},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4488360285758972},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3581897020339966},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.34755486249923706},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.20013293623924255}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7288544178009033},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5469260215759277},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4488360285758972},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3581897020339966},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.34755486249923706},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.20013293623924255},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3714462","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3714462","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/207711","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/207711","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2747329762","https://openalex.org/W2921106742","https://openalex.org/W2930957955","https://openalex.org/W3108032709","https://openalex.org/W3186138538","https://openalex.org/W3212496002","https://openalex.org/W4221152111","https://openalex.org/W4224051134","https://openalex.org/W4225108562","https://openalex.org/W4226287673","https://openalex.org/W4288055861","https://openalex.org/W4309953112","https://openalex.org/W4315706637","https://openalex.org/W4320165837","https://openalex.org/W4320490961","https://openalex.org/W4327810433","https://openalex.org/W4376122390","https://openalex.org/W4376167329","https://openalex.org/W4384918448","https://openalex.org/W4385573862","https://openalex.org/W4386185625","https://openalex.org/W4386436496","https://openalex.org/W4387030780","https://openalex.org/W4388483712","https://openalex.org/W4389519225","https://openalex.org/W4394745858"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2163672025","https://openalex.org/W2048831961","https://openalex.org/W1606349578","https://openalex.org/W4399567378"],"abstract_inverted_index":{"Recent":[0],"code":[1,20,60,94,122,153,176,181,198,294,321],"large":[2],"language":[3],"models":[4],"(LLMs)":[5],"have":[6],"shown":[7],"promising":[8],"performance":[9,243,316],"in":[10,18,36,174,244,269,292],"generating":[11,305],"standalone":[12],"functions.":[13],"However,":[14],"they":[15],"face":[16],"limitations":[17],"repository-level":[19,29,175,293],"generation":[21,62,177],"due":[22],"to":[23,64,103,118,151,169,224,232,301,319],"their":[24,112],"lack":[25],"of":[26,28,265],"awareness":[27],"dependencies":[30],"(":[31],"e.g.,":[32],"user-defined":[33],"attributes),":[34],"resulting":[35],"dependency":[37],"errors":[38],"such":[39,249],"as":[40,250],"undefined-variable":[41],"and":[42,75,79,155,185,200,208,226,255,267,276,327],"no-member":[43],"errors.":[44],"In":[45,124],"this":[46,189],"work,":[47],"we":[48,191],"introduce":[49,201],"ToolGen":[50,68,88,128,146,171,217,262,287,313],",":[51],"an":[52],"approach":[53],"that":[54,216],"integrates":[55],"autocompletion":[56,105,149],"tools":[57],"into":[58],"the":[59,85,125,137,148,157,235,259,281],"LLM":[61],"process":[63],"address":[65],"these":[66],"dependencies.":[67],"comprises":[69],"two":[70,202],"main":[71],"phases:":[72],"Trigger":[73],"Insertion":[74],"Model":[76],"Fine-tuning":[77],"(Offline),":[78],"Tool-integrated":[80],"Code":[81],"Generation":[82],"(Online).":[83],"During":[84],"offline":[86],"phase,":[87,127],"augments":[89],"functions":[90,131],"within":[91],"a":[92,97,120,141,193],"given":[93],"corpus":[95],"with":[96,111,296],"special":[98],"mark":[99,142],"token,":[100],"indicating":[101],"positions":[102],"trigger":[104],"tools.":[106],"These":[107],"augmented":[108],"functions,":[109],"along":[110],"corresponding":[113],"descriptions,":[114],"are":[115],"then":[116],"used":[117],"fine-tune":[119],"selected":[121],"LLM.":[123,139],"online":[126],"iteratively":[129],"generates":[130],"by":[132,222,230],"predicting":[133],"tokens":[134],"step-by-step":[135],"using":[136],"fine-tuned":[138],"Whenever":[140],"token":[143],"is":[144],"encountered,":[145],"invokes":[147],"tool":[150],"suggest":[152],"completions":[154],"selects":[156],"most":[158],"appropriate":[159],"one":[160],"through":[161],"constrained":[162],"greedy":[163],"search.":[164],"We":[165],"conduct":[166],"comprehensive":[167],"experiments":[168],"evaluate":[170],"\u2019s":[172,314],"effectiveness":[173],"across":[178,234],"three":[179,236],"distinct":[180],"LLMs:":[182],"CodeGPT,":[183],"CodeT5,":[184],"CodeLlama.":[186],"To":[187],"facilitate":[188],"evaluation,":[190],"create":[192],"benchmark":[194],"comprising":[195],"671":[196],"real-world":[197],"repositories":[199],"new":[203],"dependency-based":[204],"metrics:":[205],"Dependency":[206,220],"Coverage":[207,221],"Static":[209,227],"Validity":[210,228],"Rate":[211,229],".":[212],"The":[213],"results":[214],"demonstrate":[215],"significantly":[218],"improves":[219],"31.4%":[223],"39.1%":[225],"44.9%":[231],"57.7%":[233],"LLMs,":[237,322],"while":[238,279],"maintaining":[239,280],"competitive":[240],"or":[241],"improved":[242],"widely":[245],"recognized":[246],"similarity":[247],"metrics":[248],"BLEU-4,":[251],"CodeBLEU,":[252],"Edit":[253],"Similarity,":[254],"Exact":[256],"Match.":[257],"On":[258],"CoderEval":[260],"dataset,":[261],"achieves":[263],"improvements":[264],"40.0%":[266],"25.0%":[268],"test":[270],"pass":[271,283],"rate":[272,284],"(Pass@1)":[273],"for":[274,285,304],"CodeT5":[275],"CodeLlama,":[277],"respectively,":[278],"same":[282],"CodeGPT.":[286],"also":[288],"demonstrates":[289],"high":[290],"efficiency":[291],"generation,":[295],"latency":[297],"ranging":[298],"from":[299],"0.63":[300],"2.34":[302],"seconds":[303],"each":[306],"function.":[307],"Furthermore,":[308],"our":[309],"generalizability":[310],"evaluation":[311],"confirms":[312],"consistent":[315],"when":[317],"applied":[318],"diverse":[320],"encompassing":[323],"various":[324],"model":[325],"architectures":[326],"scales.":[328]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}