{"id":"https://openalex.org/W7160550956","doi":"https://doi.org/10.48550/arxiv.2605.04236","title":"Adaptive Consensus in LLM Ensembles via Sequential Evidence Accumulation: Automatic Budget Identification and Calibrated Commit Signals","display_name":"Adaptive Consensus in LLM Ensembles via Sequential Evidence Accumulation: Automatic Budget Identification and Calibrated Commit Signals","publication_year":2026,"publication_date":"2026-05-05","ids":{"openalex":"https://openalex.org/W7160550956","doi":"https://doi.org/10.48550/arxiv.2605.04236"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.04236","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04236","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.04236","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135636603","display_name":"Roberto Medina","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Medina, Roberto E.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5135636603"],"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":0.4740000069141388,"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":0.4740000069141388,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.24549999833106995,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.04320000112056732,"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/commit","display_name":"Commit","score":0.675000011920929},{"id":"https://openalex.org/keywords/deliberation","display_name":"Deliberation","score":0.6654999852180481},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.51910001039505},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4666999876499176},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.44339999556541443},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.42730000615119934},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4097999930381775},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.388700008392334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092000246047974},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.675000011920929},{"id":"https://openalex.org/C2776946740","wikidata":"https://www.wikidata.org/wiki/Q358652","display_name":"Deliberation","level":3,"score":0.6654999852180481},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42410001158714294},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38199999928474426},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35920000076293945},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2694000005722046},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.04236","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04236","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.04236","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04236","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"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":{"Large":[0],"Language":[1],"Model":[2],"ensembles":[3],"improve":[4],"reasoning":[5],"accuracy,":[6],"but":[7,173],"only":[8,145],"up":[9],"to":[10,66,109],"a":[11,27,42,55,78,162,179],"performance":[12],"boundary":[13],"beyond":[14],"which":[15],"additional":[16],"deliberation":[17,33],"degrades":[18],"accuracy.":[19,139],"We":[20,48],"introduce":[21],"DASE":[22,53],"(Deliberative":[23],"Adaptive":[24,133],"Stopping":[25],"Ensemble),":[26],"stopping":[28],"heuristic":[29],"for":[30,144],"iterative":[31],"ensemble":[32],"that":[34,59],"commits":[35,97],"early":[36],"on":[37,45,127],"genuine":[38],"consensus":[39],"and":[40,63,178],"applies":[41],"global-frequency":[43],"fallback":[44],"fragmented":[46],"evidence.":[47],"make":[49],"three":[50],"contributions.":[51],"(1)":[52],"produces":[54],"commit-type":[56],"routing":[57,81,130,165],"partition":[58,76],"generalises":[60],"across":[61],"benchmarks":[62],"is":[64,194],"complementary":[65],"verbalized":[67,113],"single-call":[68],"confidence.":[69],"On":[70,88,140,149],"GPQA-Extended":[71,150],"(N=546,":[72],"70B":[73],"ensemble),":[74],"the":[75,123,152],"yields":[77],"39.5":[79],"pp":[80,105,119,147,164,182],"gap":[82],"(right-wall":[83],"81.1%":[84],"vs.":[85,101],"left-wall":[86,102],"41.5%).":[87],"AIME":[89],"2010-2023":[90],"(N=261,":[91],"120B":[92,153],"ensemble,":[93],"3":[94],"seeds),":[95],"right-wall":[96,176],"reach":[98],"98.3%":[99],"accuracy":[100],"72.8%":[103],"(25.5":[104],"gap),":[106],"statistically":[107],"equivalent":[108],"Opus":[110],"4.6":[111],"Standard":[112],"confidence":[114],"at":[115,151],"matched":[116],"coverage":[117,177],"(25.7":[118],"gap;":[120,166],"bootstrap":[121],"p=0.873);":[122],"two":[124],"mechanisms":[125],"disagree":[126],"37%":[128],"of":[129],"assignments.":[131],"(2)":[132],"stopping,":[134],"not":[135],"injection":[136,156,168],"bandwidth,":[137],"drives":[138],"AIME-300,":[141],"bandwidth":[142],"accounts":[143],"0.3":[146],"(ns).":[148],"tier,":[154],"sparse":[155],"($\\approx15$":[157],"tokens/worker/round)":[158],"achieves":[159,171],"70.9%":[160],"with":[161,174],"30.7":[163],"dense":[167],"($\\approx600$":[169],"chars/worker/round)":[170],"72.2%":[172],"halved":[175],"narrower":[180],"18.9":[181],"gap.":[183],"(3)":[184],"Injection-based":[185],"methods":[186],"exhibit":[187],"an":[188],"inverted-U":[189],"accuracy-vs-inference":[190],"trajectory;":[191],"this":[192],"pattern":[193],"hypothesis-generating.":[195]},"counts_by_year":[],"updated_date":"2026-05-16T06:04:12.930555","created_date":"2026-05-08T00:00:00"}