{"id":"https://openalex.org/W7137823514","doi":"https://doi.org/10.1609/aaai.v40i19.38692","title":"Inference Scaling Law for Retrieval Augmented Generation","display_name":"Inference Scaling Law for Retrieval Augmented Generation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137823514","doi":"https://doi.org/10.1609/aaai.v40i19.38692"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i19.38692","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i19.38692","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38692/42654","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38692/42654","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129681584","display_name":"Shu Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shu Zhou","raw_affiliation_strings":["School of Information Management, Nanjing University, China\nKey Laboratory of Data Engineering and Knowledge Services in Jiangsu Provincial Universities (Nanjing University), China\nJiangsu International Joint Informatics Laboratory, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"School of Information Management, Nanjing University, China\nKey Laboratory of Data Engineering and Knowledge Services in Jiangsu Provincial Universities (Nanjing University), China\nJiangsu International Joint Informatics Laboratory, Nanjing University, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120950142","display_name":"yuxuan ao","orcid":null},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Ao","raw_affiliation_strings":["School of Information Management, Nanjing University, China\nKey Laboratory of Data Engineering and Knowledge Services in Jiangsu Provincial Universities (Nanjing University), China\nJiangsu International Joint Informatics Laboratory, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"School of Information Management, Nanjing University, China\nKey Laboratory of Data Engineering and Knowledge Services in Jiangsu Provincial Universities (Nanjing University), China\nJiangsu International Joint Informatics Laboratory, Nanjing University, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129673603","display_name":"Yunyang Xuan","orcid":null},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunyang Xuan","raw_affiliation_strings":["School of Information Management, Nanjing University, China\nKey Laboratory of Data Engineering and Knowledge Services in Jiangsu Provincial Universities (Nanjing University), China\nJiangsu International Joint Informatics Laboratory, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"School of Information Management, Nanjing University, China\nKey Laboratory of Data Engineering and Knowledge Services in Jiangsu Provincial Universities (Nanjing University), China\nJiangsu International Joint Informatics Laboratory, Nanjing University, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129730964","display_name":"Xin Eric Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Baidu Inc, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129701946","display_name":"Tao Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I137056471","display_name":"Nanjing University of Finance and Economics","ror":"https://ror.org/031y8am81","country_code":"CN","type":"education","lineage":["https://openalex.org/I137056471"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Fan","raw_affiliation_strings":["School of Public Administration, Nanjing University of Finance & Economics, China"],"affiliations":[{"raw_affiliation_string":"School of Public Administration, Nanjing University of Finance & Economics, China","institution_ids":["https://openalex.org/I137056471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129641638","display_name":"Hao Henry Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["School of Information Management, Nanjing University, China\nKey Laboratory of Data Engineering and Knowledge Services in Jiangsu Provincial Universities (Nanjing University), China\nJiangsu International Joint Informatics Laboratory, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"School of Information Management, Nanjing University, China\nKey Laboratory of Data Engineering and Knowledge Services in Jiangsu Provincial Universities (Nanjing University), China\nJiangsu International Joint Informatics Laboratory, Nanjing University, China","institution_ids":["https://openalex.org/I200845125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5129681584"],"corresponding_institution_ids":["https://openalex.org/I200845125"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04643035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"19","first_page":"16522","last_page":"16530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.44200000166893005,"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":0.44200000166893005,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2240000069141388,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.11289999634027481,"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/inference","display_name":"Inference","score":0.8680999875068665},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6176999807357788},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5605999827384949},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5260999798774719},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4530999958515167},{"id":"https://openalex.org/keywords/scaling-law","display_name":"Scaling law","score":0.3790999948978424},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3303999900817871}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8680999875068665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742900013923645},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6176999807357788},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5605999827384949},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48010000586509705},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40290001034736633},{"id":"https://openalex.org/C2988430800","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Scaling law","level":3,"score":0.3790999948978424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2775999903678894},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C2779793024","wikidata":"https://www.wikidata.org/wiki/Q17299941","display_name":"Indirect Inference","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i19.38692","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i19.38692","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38692/42654","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i19.38692","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i19.38692","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38692/42654","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5158290266990662,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6152536712","display_name":null,"funder_award_id":"010814370338","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7694383859","display_name":null,"funder_award_id":"72074108","funder_id":"https://openalex.org/F4320324852","funder_display_name":"Nanjing University"},{"id":"https://openalex.org/G8524424817","display_name":null,"funder_award_id":"72074108","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137823514.pdf","grobid_xml":"https://content.openalex.org/works/W7137823514.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"has":[3,31],"recently":[4],"emerged":[5],"as":[6],"a":[7,51,112],"powerful":[8],"framework":[9],"for":[10,58,146],"knowledge-intensive":[11],"natural":[12],"language":[13,23],"processing":[14],"tasks,":[15],"which":[16,61],"leverages":[17],"the":[18,34,121,128,144],"strengths":[19],"of":[20,37,54,80,131,151],"both":[21],"pre-trained":[22],"models":[24,133,153],"and":[25,83,101,107,148],"external":[26],"knowledge.":[27],"While":[28],"significant":[29],"progress":[30],"been":[32],"made,":[33],"scaling":[35,56,96,115,123],"behavior":[36],"these":[38,105],"approaches":[39],"during":[40],"inference":[41,55,64,114],"remains":[42],"poorly":[43],"understood.":[44],"Towards":[45],"this":[46,48],"end,":[47],"paper":[49],"presents":[50],"comprehensive":[52],"study":[53],"law":[57,116],"RAG":[59,132,152],"models,":[60],"investigates":[62],"how":[63],"performance":[65,129],"scales":[66],"with":[67,117],"respect":[68],"to":[69],"key":[70],"factors":[71,106],"including":[72],"retriever":[73],"model":[74,77],"scale,":[75,78],"generator":[76],"number":[79],"retrieved":[81],"documents,":[82],"context":[84],"window":[85],"size.":[86],"Through":[87],"extensive":[88],"experiments":[89],"on":[90],"benchmark":[91],"datasets,":[92],"we":[93,125],"establish":[94],"empirical":[95],"laws":[97],"that":[98],"reveal":[99],"power-law":[100],"sigmoid-type":[102],"relationships":[103],"between":[104],"performance.":[108],"We":[109,138],"further":[110],"build":[111],"joint":[113],"theoretical":[118],"justification.":[119],"With":[120],"proposed":[122],"laws,":[124],"can":[126,142],"understand":[127],"tendency":[130],"under":[134],"different":[135],"computational":[136],"resources.":[137],"believe":[139],"our":[140],"insights":[141],"pave":[143],"way":[145],"efficient":[147],"effective":[149],"deployment":[150],"in":[154],"more":[155],"applications.":[156]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-03-18T00:00:00"}