{"id":"https://openalex.org/W7163014859","doi":"https://doi.org/10.48550/arxiv.2605.31176","title":"Retriever Portfolios: A Principled Approach to Adaptive RAG","display_name":"Retriever Portfolios: A Principled Approach to Adaptive RAG","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163014859","doi":"https://doi.org/10.48550/arxiv.2605.31176"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.31176","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31176","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.31176","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137537929","display_name":"Miltiadis Stouras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stouras, Miltiadis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074251728","display_name":"Vincent Cohen-Addad","orcid":"https://orcid.org/0000-0002-0779-8962"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cohen-Addad, Vincent","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022550622","display_name":"Silvio Lattanzi","orcid":"https://orcid.org/0000-0002-3502-7559"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lattanzi, Silvio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137567368","display_name":"Ola Svensson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Svensson, Ola","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":false,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.4546999931335449,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.4546999931335449,"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/T10028","display_name":"Topic Modeling","score":0.25619998574256897,"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":0.12290000170469284,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6510999798774719},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.548799991607666},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5264000296592712},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.47099998593330383},{"id":"https://openalex.org/keywords/router","display_name":"Router","score":0.41510000824928284},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3716000020503998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663999795913696},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6510999798774719},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.548799991607666},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4717999994754791},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3467000126838684},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2597000002861023},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.31176","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31176","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.31176","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31176","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"systems":[3],"typically":[4],"rely":[5],"on":[6,104],"a":[7,11,33,38,47],"single":[8,12],"retriever":[9],"and":[10,74,94,100,108,124,137],"set":[13],"of":[14,42,50,56],"hyperparameters,":[15],"despite":[16],"facing":[17],"highly":[18],"heterogeneous":[19],"queries":[20],"that":[21,35,76],"range":[22],"from":[23,46],"simple":[24],"factoid":[25],"questions":[26],"to":[27,52,114],"complex":[28],"multi-hop":[29],"reasoning.":[30],"We":[31,61],"propose":[32],"method":[34],"automatically":[36],"selects":[37],"small,":[39],"diverse":[40],"subset":[41],"retrievers":[43],"(a":[44],"portfolio)":[45],"large":[48],"pool":[49],"candidates,":[51],"cover":[53],"different":[54],"regions":[55],"the":[57,71],"target":[58],"query":[59,72],"distribution.":[60],"formalize":[62],"this":[63],"setting":[64],"via":[65],"an":[66,79],"expected":[67],"best-of-$k$":[68],"objective":[69],"over":[70],"distribution":[73],"show":[75],"it":[77],"admits":[78],"efficient":[80],"portfolio":[81],"construction":[82],"algorithm":[83],"with":[84,133],"near-optimal":[85],"guarantees.":[86],"Across":[87],"multiple":[88],"QA":[89],"benchmarks,":[90],"our":[91],"learned":[92],"portfolios":[93,120],"router":[95],"pipeline":[96],"consistently":[97],"outperform":[98],"single-retriever":[99],"naive":[101],"multi-retriever":[102],"baselines":[103],"both":[105],"retrieval":[106,123],"metrics":[107],"answer":[109],"quality.":[110],"In":[111],"addition,":[112],"compared":[113],"inference-time":[115],"hyperparameter":[116],"tuning":[117],"approaches,":[118],"fixed":[119],"enable":[121],"parallel":[122],"LLM":[125],"calls,":[126],"achieving":[127],"comparable":[128],"(and":[129],"sometimes":[130],"better)":[131],"accuracy":[132],"substantially":[134],"lower":[135],"latency":[136],"token":[138],"cost.":[139]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-02T00:00:00"}