{"id":"https://openalex.org/W4417106887","doi":"https://doi.org/10.48550/arxiv.2508.02611","title":"Meta-RAG on Large Codebases Using Code Summarization","display_name":"Meta-RAG on Large Codebases Using Code Summarization","publication_year":2025,"publication_date":"2025-08-04","ids":{"openalex":"https://openalex.org/W4417106887","doi":"https://doi.org/10.48550/arxiv.2508.02611"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.02611","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02611","pdf_url":"https://arxiv.org/pdf/2508.02611","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/2508.02611","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007634904","display_name":"Vali Tawosi","orcid":"https://orcid.org/0000-0001-5052-672X","observed_orcids":["https://orcid.org/0000-0001-5052-672X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tawosi, Vali","raw_affiliation_strings":["AI Research , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research , UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082203057","display_name":"Salwa Alamir","orcid":"https://orcid.org/0009-0006-6650-7041","observed_orcids":["https://orcid.org/0009-0006-6650-7041"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alamir, Salwa","raw_affiliation_strings":["AI Research , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research , UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048424819","display_name":"Xiaomo Liu","orcid":"https://orcid.org/0000-0003-4184-4202","observed_orcids":["https://orcid.org/0000-0003-4184-4202"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xiaomo","raw_affiliation_strings":["JP Morgan AI Research , US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JP Morgan AI Research , US","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088276691","display_name":"Manuela Veloso","orcid":"https://orcid.org/0000-0001-6738-238X","observed_orcids":["https://orcid.org/0000-0001-6738-238X","https://orcid.org/0000-0001-5355-1912"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Veloso, Manuela","raw_affiliation_strings":["JP Morgan AI Research , US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JP Morgan AI Research , US","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"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/T10260","display_name":"Software Engineering Research","score":0.9932000041007996,"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":0.9932000041007996,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.006399999838322401,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.0,"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":0.9649999737739563},{"id":"https://openalex.org/keywords/code-summarization","display_name":"code summarization","score":0.8209999799728394},{"id":"https://openalex.org/keywords/bug-localization","display_name":"bug localization","score":0.9729999899864197},{"id":"https://openalex.org/keywords/large-codebases","display_name":"large codebases","score":0.9020000100135803},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.902999997138977},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7450000047683716},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.6669999957084656},{"id":"https://openalex.org/keywords/code-maintenance","display_name":"code maintenance","score":0.6019999980926514},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.6539999842643738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8988999724388123},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.8531000018119812},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7239000201225281},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6284000277519226},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5479000210762024},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4925000071525574},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48350000381469727},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4790000021457672},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37950000166893005},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.3675000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.359499990940094},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.321399986743927},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.2964000105857849},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.26579999923706055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26089999079704285},{"id":"https://openalex.org/C2777062904","wikidata":"https://www.wikidata.org/wiki/Q545406","display_name":"Toolchain","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.25440001487731934},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2508.02611","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02611","pdf_url":"https://arxiv.org/pdf/2508.02611","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.2508.02611","doi":"https://doi.org/10.48550/arxiv.2508.02611","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.02611","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:2508.02611","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02611","pdf_url":"https://arxiv.org/pdf/2508.02611","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/W4417106887.pdf","grobid_xml":"https://content.openalex.org/works/W4417106887.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1985947101","https://openalex.org/W2249980257","https://openalex.org/W2617591873","https://openalex.org/W2729710884","https://openalex.org/W2921988748","https://openalex.org/W3146720657","https://openalex.org/W3149255455","https://openalex.org/W3155283289","https://openalex.org/W3195140297","https://openalex.org/W4385327683","https://openalex.org/W4387561453","https://openalex.org/W4387636003","https://openalex.org/W4389158474","https://openalex.org/W4393942918","https://openalex.org/W4398229654","https://openalex.org/W4402442868","https://openalex.org/W4402500779","https://openalex.org/W4406459629","https://openalex.org/W4411449940","https://openalex.org/W4411551762","https://openalex.org/W4411552177","https://openalex.org/W4411552740","https://openalex.org/W4412886942","https://openalex.org/W6967084484","https://openalex.org/W7103754783","https://openalex.org/W7125135101"],"related_works":["https://openalex.org/W7161728255","https://openalex.org/W7168280178","https://openalex.org/W4412045934","https://openalex.org/W4406459629","https://openalex.org/W4411359851","https://openalex.org/W7113915831","https://openalex.org/W4415101712","https://openalex.org/W4411449803","https://openalex.org/W7133188732","https://openalex.org/W7129594874"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Model":[2],"(LLM)":[3],"systems":[4],"have":[5,29],"been":[6],"at":[7],"the":[8,31,57,123,135,142],"forefront":[9],"of":[10,19,33,36,59,103,122,137],"applied":[11],"Artificial":[12],"Intelligence":[13],"(AI)":[14],"research":[15],"in":[16,73],"a":[17,34,45,67,85,106],"multitude":[18],"domains.":[20],"One":[21],"such":[22],"domain":[23],"is":[24,44],"software":[25],"development,":[26],"where":[27,93],"researchers":[28],"pushed":[30],"automation":[32],"number":[35],"code":[37,52,60],"tasks":[38],"through":[39,139],"LLM":[40,116],"agents.":[41],"Software":[42],"development":[43],"complex":[46],"ecosystem,":[47],"that":[48],"stretches":[49],"far":[50],"beyond":[51],"implementation":[53],"and":[54,80,150,155],"well":[55],"into":[56,105],"realm":[58],"maintenance.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,94],"propose":[66],"multi-agent":[68],"system":[69,83],"to":[70,97,118],"localize":[71],"bugs":[72],"large":[74],"pre-existing":[75],"codebases":[76,99],"using":[77],"information":[78],"retrieval":[79],"LLMs.":[81],"Our":[82],"introduces":[84],"novel":[86],"Retrieval":[87],"Augmented":[88],"Generation":[89],"(RAG)":[90],"approach,":[91],"Meta-RAG,":[92],"utilize":[95],"summaries":[96],"condense":[98],"by":[100],"an":[101,115],"average":[102],"79.8\\%,":[104],"compact,":[107],"structured,":[108],"natural":[109],"language":[110],"representation.":[111],"We":[112,133],"then":[113],"use":[114],"agent":[117],"determine":[119],"which":[120],"parts":[121],"codebase":[124],"are":[125],"critical":[126],"for":[127,153],"bug":[128,131],"resolution,":[129],"i.e.":[130],"localization.":[132],"demonstrate":[134],"usefulness":[136],"Meta-RAG":[138,146],"evaluation":[140],"with":[141],"SWE-bench":[143],"Lite":[144],"dataset.":[145],"scores":[147],"84.67":[148],"%":[149,152],"53.0":[151],"file-level":[154],"function-level":[156],"correct":[157],"localization":[158],"rates,":[159],"respectively,":[160],"achieving":[161],"state-of-the-art":[162],"performance.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-10T00:00:00"}