{"id":"https://openalex.org/W7160593552","doi":"https://doi.org/10.48550/arxiv.2605.05245","title":"AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation","display_name":"AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation","publication_year":2026,"publication_date":"2026-05-04","ids":{"openalex":"https://openalex.org/W7160593552","doi":"https://doi.org/10.48550/arxiv.2605.05245"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.05245","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05245","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,"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.2605.05245","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135706123","display_name":"Yilin Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yilin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135659016","display_name":"Yinshan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yinshan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135713023","display_name":"Yixuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yixuan","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":0.38530001044273376,"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":0.38530001044273376,"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":0.26489999890327454,"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":0.10750000178813934,"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/robustness","display_name":"Robustness (evolution)","score":0.6507999897003174},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6177999973297119},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.541100025177002},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.461899995803833},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4205999970436096},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.40860000252723694},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4050999879837036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7207000255584717},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6507999897003174},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6177999973297119},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.461899995803833},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4032999873161316},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38179999589920044},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.26739999651908875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.05245","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05245","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,"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.2605.05245","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05245","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,"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":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4357525706291199}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"remains":[3],"brittle":[4],"on":[5,106,132],"multi-hop":[6,66,163],"questions":[7],"in":[8,162],"realistic":[9],"deployment":[10],"settings,":[11,119],"where":[12],"retrieved":[13],"evidence":[14,63,70,124,158],"may":[15],"be":[16,25],"noisy":[17],"or":[18,49],"redundant":[19],"and":[20,86,99,111,135,170],"only":[21],"limited":[22],"context":[23,41],"can":[24],"passed":[26],"to":[27],"the":[28,122,127],"generator.":[29],"Existing":[30],"controllers":[31],"address":[32],"parts":[33],"of":[34],"this":[35],"problem,":[36],"but":[37],"typically":[38],"either":[39],"expand":[40],"additively,":[42],"select":[43],"from":[44],"a":[45,61,73,87],"fixed":[46],"top-k":[47],"set,":[48],"optimize":[50],"relevance":[51],"without":[52],"explicitly":[53],"repairing":[54],"missing":[55],"bridge":[56],"facts.":[57],"We":[58,103],"propose":[59],"AdaGATE,":[60],"training-free":[62],"controller":[64],"for":[65],"RAG":[67,164],"that":[68,92,151],"frames":[69],"selection":[71,90],"as":[72],"token-constrained":[74],"repair":[75],"problem.":[76],"AdaGATE":[77,105,120],"combines":[78],"entity":[79],"centric":[80],"gap":[81,94],"tracking,":[82],"targeted":[83],"micro-query":[84],"generation,":[85],"utility":[88],"based":[89],"mechanism":[91],"balances":[93],"coverage,":[95],"corroboration,":[96],"novelty,":[97],"redundancy,":[98,110],"direct":[100],"question":[101],"relevance.":[102],"evaluate":[104],"HotpotQA":[107],"under":[108,137,165],"clean,":[109],"noise":[112],"injected":[113],"retrieval":[114],"conditions.":[115],"Across":[116],"all":[117],"three":[118],"achieves":[121],"best":[123],"F1":[125],"among":[126],"compared":[128],"controllers,":[129],"reaching":[130],"62.3%":[131],"clean":[133],"data":[134],"71.2%":[136],"redundancy":[138],"injection,":[139],"while":[140],"using":[141],"2.6x":[142],"fewer":[143],"input":[144],"tokens":[145],"than":[146],"Adaptive-k.":[147],"These":[148],"results":[149],"suggest":[150],"explicit":[152],"gap-aware":[153],"repair,":[154],"combined":[155],"with":[156],"token-efficient":[157],"selection,":[159],"improves":[160],"robustness":[161],"imperfect":[166],"retrieval.":[167],"Our":[168],"code":[169],"evaluation":[171],"pipeline":[172],"are":[173],"available":[174],"at":[175],"https://github.com/eliguo/AdaGATE.":[176]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-09T00:00:00"}