{"id":"https://openalex.org/W7164858455","doi":"https://doi.org/10.48550/arxiv.2606.13814","title":"TASR: Training-Free Adaptive Stopping for Iterative Retrieval","display_name":"TASR: Training-Free Adaptive Stopping for Iterative Retrieval","publication_year":2026,"publication_date":"2026-06-11","ids":{"openalex":"https://openalex.org/W7164858455","doi":"https://doi.org/10.48550/arxiv.2606.13814"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.13814","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.13814","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.2606.13814","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107555237","display_name":"Adrian Kieback","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kieback, Adrian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047556922","display_name":"Uyiosa Philip Amadasun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amadasun, Uyiosa Philip","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138656668","display_name":"Aman Chadha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chadha, Aman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138682942","display_name":"Aaron Elkins","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elkins, Aaron","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/T10028","display_name":"Topic Modeling","score":0.2547000050544739,"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":0.2547000050544739,"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":0.14100000262260437,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.05959999933838844,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.557200014591217},{"id":"https://openalex.org/keywords/early-stopping","display_name":"Early stopping","score":0.5278000235557556},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4945000112056732},{"id":"https://openalex.org/keywords/stopping-rule","display_name":"Stopping rule","score":0.41769999265670776},{"id":"https://openalex.org/keywords/logit","display_name":"Logit","score":0.387800008058548},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.3522999882698059},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.3490999937057495},{"id":"https://openalex.org/keywords/optimal-stopping","display_name":"Optimal stopping","score":0.3398999869823456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5814999938011169},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.557200014591217},{"id":"https://openalex.org/C5465570","wikidata":"https://www.wikidata.org/wiki/Q5326898","display_name":"Early stopping","level":3,"score":0.5278000235557556},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.430400013923645},{"id":"https://openalex.org/C2983961125","wikidata":"https://www.wikidata.org/wiki/Q1288707","display_name":"Stopping rule","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39980000257492065},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.3490999937057495},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3431999981403351},{"id":"https://openalex.org/C99414536","wikidata":"https://www.wikidata.org/wiki/Q7098950","display_name":"Optimal stopping","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.3118000030517578},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C99888217","wikidata":"https://www.wikidata.org/wiki/Q1288707","display_name":"Stopping time","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2680000066757202},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.13814","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.13814","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.2606.13814","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.13814","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":[{"id":"https://metadata.un.org/sdg/16","score":0.6651204228401184,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Iterative":[0],"retrieval-augmented":[1],"generation":[2],"agents":[3],"commonly":[4],"overspend":[5],"by":[6,124],"continuing":[7],"to":[8,41],"retrieve":[9],"after":[10],"the":[11,23,26,39,67,75,89,151,192,222,231],"model":[12,51,68,236],"has":[13],"converged":[14],"on":[15,130,154,163,191,210],"an":[16,183,240],"answer,":[17],"incurring":[18],"calls":[19,120,139],"that":[20,45,64,205],"change":[21],"neither":[22],"prediction":[24],"nor":[25],"supporting":[27],"evidence.":[28],"Existing":[29],"remedies":[30],"learn":[31],"a":[32,42,61,103,167,234],"stopping":[33,189,247],"policy":[34],"from":[35,150,182],"labeled":[36],"trajectories,":[37],"tying":[38],"decision":[40],"trained":[43],"component":[44],"requires":[46],"retraining":[47],"for":[48,144,245],"each":[49],"new":[50],"or":[52,84],"task.":[53],"We":[54],"propose":[55],"TASR":[56,109,238],"(Training-Free":[57],"Adaptive":[58],"Stopping":[59],"Rule),":[60],"one-line":[62],"predicate":[63],"fires":[65],"when":[66],"repeats":[69],"its":[70,119],"previous-round":[71],"normalized":[72],"answer":[73],"and":[74,121,162],"isotonically":[76],"calibrated":[77],"logit":[78,223],"margin":[79,224],"exceeds":[80,122],"0.25.":[81],"No":[82],"classifier":[83],"value":[85],"head":[86],"is":[87,91,239,252],"learned;":[88],"threshold":[90],"fixed":[92],"across":[93,158],"all":[94],"thirty-two":[95],"(model,":[96],"retriever,":[97],"corpus)":[98],"configurations":[99],"we":[100],"evaluate.":[101],"On":[102],"3-model":[104],"x":[105],"2-dataset":[106],"distractor":[107,152],"grid,":[108],"retains":[110],"94.8%":[111],"of":[112,118,166,186,214],"fixed-k=5's":[113],"macro":[114],"F1":[115,136],"at":[116,137,142,255],"62.6%":[117],"fixed-k=3":[123],"+3.42":[125],"F1.":[126],"The":[127,178],"pattern":[128],"holds":[129],"nine":[131,155],"open-domain":[132],"BM25":[133],"cells":[134,157,165],"(55.01":[135],"2.98":[138],"vs.":[140],"54.33":[141],"3.00":[143],"fixed-k=3)":[145],"and,":[146],"with":[147,171],"calibration":[148],"locked":[149],"split,":[153],"dense-retrieval":[156],"two":[159],"retriever":[160],"families,":[161],"eight":[164],"Nemotron-3-Ultra-550B":[168],"production":[169],"model,":[170],"zero":[172],"significant":[173],"regressions":[174],"in":[175,233,248],"any":[176],"extension.":[177],"rule":[179],"was":[180],"selected":[181],"exhaustive":[184],"enumeration":[185],"381":[187],"candidate":[188],"rules":[190],"canonical":[193],"selection":[194],"cell,":[195],"where":[196],"no":[197],"alternative":[198],"Pareto-dominates":[199],"it.":[200],"A":[201],"signal-quality":[202],"analysis":[203],"shows":[204],"verbalized":[206],"1-5":[207],"confidence":[208],"collapses":[209],"RLHF-tuned":[211],"models":[212],"(96.5%":[213],"values":[215],"equal":[216],"5,":[217],"entropy":[218],"0.182":[219],"nats),":[220],"while":[221],"achieves":[225],"40x":[226],"better":[227],"class-conditional":[228],"separation,":[229],"grounding":[230],"design":[232],"measurable":[235],"pathology.":[237],"auditable,":[241],"training-free":[242],"Pareto":[243],"baseline":[244],"adaptive":[246],"iterative":[249],"retrieval.":[250],"Code":[251],"publicly":[253],"available":[254],"https://github.com/JSBAICenter/TASR":[256]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-16T00:00:00"}