{"id":"https://openalex.org/W7221784450","doi":"https://doi.org/10.48550/arxiv.2610.17760","title":"Gaussian Process Bandits for AI System Optimization with Selectively Verified Feedback","display_name":"Gaussian Process Bandits for AI System Optimization with Selectively Verified Feedback","publication_year":2026,"publication_date":"2026-10-13","ids":{"openalex":"https://openalex.org/W7221784450","doi":"https://doi.org/10.48550/arxiv.2610.17760"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.17760","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.17760","pdf_url":"https://arxiv.org/pdf/2610.17760","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.17760","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5158697566","display_name":"Shuang Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wu, Shuang","raw_affiliation_strings":["UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5158697566"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0,"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/gaussian-process-bandits","display_name":"Gaussian process bandits","score":0.9950000047683716},{"id":"https://openalex.org/keywords/audit-design","display_name":"audit design","score":0.6100000143051147},{"id":"https://openalex.org/keywords/reproducing-kernel-hilbert-space","display_name":"reproducing kernel Hilbert space","score":0.8100000023841858},{"id":"https://openalex.org/keywords/adaptive-allocation","display_name":"adaptive allocation","score":0.5720000267028809},{"id":"https://openalex.org/keywords/prompt-optimization","display_name":"prompt optimization","score":0.5440000295639038},{"id":"https://openalex.org/keywords/retrieval-systems","display_name":"retrieval systems","score":0.49799999594688416},{"id":"https://openalex.org/keywords/agent-workflows","display_name":"agent workflows","score":0.6230000257492065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7099000215530396},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6450999975204468},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.534500002861023},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4512999951839447},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.413100004196167},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2953999936580658},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2879999876022339},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2694999873638153},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.17760","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.17760","pdf_url":"https://arxiv.org/pdf/2610.17760","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.17760","doi":"https://doi.org/10.48550/arxiv.2610.17760","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.17760","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,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.17760","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.17760","pdf_url":"https://arxiv.org/pdf/2610.17760","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221784450.pdf","grobid_xml":"https://content.openalex.org/works/W7221784450.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W3059354130","https://openalex.org/W4399794441","https://openalex.org/W4407215871","https://openalex.org/W4417538992","https://openalex.org/W7126183217","https://openalex.org/W7127166598","https://openalex.org/W7160653712","https://openalex.org/W7168159617","https://openalex.org/W7212035784","https://openalex.org/W7213927937","https://openalex.org/W7215049327","https://openalex.org/W7220712756"],"related_works":["https://openalex.org/W2627076442","https://openalex.org/W7204207599","https://openalex.org/W7223005018","https://openalex.org/W3199516780","https://openalex.org/W1481631336","https://openalex.org/W4226124784","https://openalex.org/W2951665052","https://openalex.org/W7214708266","https://openalex.org/W7204211447","https://openalex.org/W7223293283"],"abstract_inverted_index":{"Gaussian":[0],"process":[1],"bandits":[2],"exploit":[3],"similarities":[4],"among":[5],"configurations":[6],"to":[7,100,166],"optimize":[8],"prompts,":[9],"retrieval":[10],"systems,":[11],"and":[12,42,58,83,96,122,131,156,189,201],"agent":[13],"workflows.":[14],"In":[15],"these":[16,65,148],"applications,":[17],"however,":[18],"inexpensive":[19],"model-based":[20],"evaluations":[21],"can":[22,184,192],"disagree":[23],"with":[24,80,112],"trusted":[25,43],"task":[26],"outcomes.":[27],"We":[28,70],"study":[29],"selective":[30],"verification":[31],"when":[32],"an":[33,48,152],"action":[34],"is":[35,40,45,179],"chosen":[36],"before":[37],"a":[38,59,72,85,92,118,209],"diagnostic":[39,52],"observed":[41],"feedback":[44,199],"informative":[46,102],"on":[47],"unknown":[49],"set":[50],"of":[51,68,208],"states.":[53],"A":[54,104],"finite":[55,60],"reliability":[56,78,133],"class":[57],"RKHS":[61],"signal":[62],"dictionary":[63],"describe":[64],"two":[66],"sources":[67],"uncertainty.":[69],"construct":[71],"fixed":[73,168],"audit":[74,94,137],"design":[75,111,169],"that":[76,89],"combines":[77],"coverage":[79],"reward":[81,143],"separation":[82],"establish":[84],"finite-time":[86],"regret":[87,164],"bound":[88],"accounts":[90],"for":[91],"hard":[93],"budget":[95],"the":[97,141,167,171,186],"rounds":[98],"needed":[99],"obtain":[101],"observations.":[103],"safe":[105],"adaptive":[106,153,160],"extension":[107],"mixes":[108],"this":[109],"robust":[110],"predictable":[113],"Chernoff":[114],"allocations":[115],"while":[116],"preserving":[117],"uniform":[119],"identification":[120],"floor":[121],"exact":[123,172],"expected":[124],"acquisition-cost":[125],"accounting.":[126],"For":[127],"signed-coordinate":[128],"kernels,":[129],"structured":[130],"diffuse":[132],"classes":[134],"require":[135],"different":[136],"scales":[138],"despite":[139],"sharing":[140],"same":[142],"geometry.":[144],"Synthetic":[145],"experiments":[146],"distinguish":[147],"certified":[149],"designs":[150],"from":[151],"posterior":[154],"heuristic":[155],"GP":[157],"controls.":[158],"Safe":[159],"allocation":[161],"reduces":[162],"aggregate":[163],"relative":[165],"under":[170],"dictionary,":[173],"but":[174],"its":[175],"finite-budget":[176],"error":[177],"certificate":[178],"numerically":[180],"loose.":[181],"Conditional-feedback":[182],"errors":[183],"remove":[185],"heuristic's":[187],"advantage":[188],"target":[190],"perturbations":[191],"reverse":[193],"it.":[194],"Separate":[195],"AI-task":[196],"replays":[197],"assess":[198],"correction":[200],"fitted-dictionary":[202],"policies":[203],"without":[204],"establishing":[205],"end-to-end":[206],"validation":[207],"learned":[210],"selective-verification":[211],"method.":[212]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-15T00:00:00"}