{"id":"https://openalex.org/W7212035784","doi":"https://doi.org/10.48550/arxiv.2609.05820","title":"Online Learning with LLM Experts from Limited Feedback","display_name":"Online Learning with LLM Experts from Limited Feedback","publication_year":2026,"publication_date":"2026-09-05","ids":{"openalex":"https://openalex.org/W7212035784","doi":"https://doi.org/10.48550/arxiv.2609.05820"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.05820","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.05820","pdf_url":"https://arxiv.org/pdf/2609.05820","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/2609.05820","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151088612","display_name":"Wang Wei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047754690","display_name":"Soumyabrata Pal","orcid":"https://orcid.org/0000-0003-2949-3761","observed_orcids":["https://orcid.org/0000-0003-2949-3761"]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pal, Soumyabrata","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151014971","display_name":"Koyel Mukherjee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mukherjee, Koyel","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028863551","display_name":"Franck Dernoncourt","orcid":"https://orcid.org/0000-0002-1119-1346","observed_orcids":["https://orcid.org/0000-0002-1119-1346"]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dernoncourt, Franck","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009957887","display_name":"Ryan A. Rossi","orcid":"https://orcid.org/0000-0001-9758-0635","observed_orcids":["https://orcid.org/0000-0001-9758-0635"]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rossi, Ryan A.","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049020775","display_name":"Branislav Kveton","orcid":"https://orcid.org/0000-0002-3965-1367","observed_orcids":["https://orcid.org/0000-0002-3965-1367"]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kveton, Branislav","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038305381","display_name":"Hoda Eldardiry","orcid":"https://orcid.org/0000-0002-9712-6667","observed_orcids":["https://orcid.org/0000-0002-9712-6667"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eldardiry, Hoda","raw_affiliation_strings":["Virginia Tech ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech ,","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T12288","display_name":"Optimization and Search Problems","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.6570000052452087},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8230000138282776},{"id":"https://openalex.org/keywords/prompt-routing","display_name":"prompt routing","score":0.6819999814033508},{"id":"https://openalex.org/keywords/multi-armed-bandits","display_name":"multi-armed bandits","score":0.6940000057220459},{"id":"https://openalex.org/keywords/regret-minimization","display_name":"regret minimization","score":0.8550000190734863},{"id":"https://openalex.org/keywords/limited-feedback","display_name":"limited feedback","score":0.9340000152587891},{"id":"https://openalex.org/keywords/expert-selection","display_name":"expert selection","score":0.6370000243186951},{"id":"https://openalex.org/keywords/llm-ensembles","display_name":"LLM ensembles","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8062000274658203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6646999716758728},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.6116999983787537},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5611000061035156},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5552999973297119},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5020999908447266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41769999265670776},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C27548731","wikidata":"https://www.wikidata.org/wiki/Q88272","display_name":"Investment (military)","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.25929999351501465},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2540000081062317},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.05820","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.05820","pdf_url":"https://arxiv.org/pdf/2609.05820","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.2609.05820","doi":"https://doi.org/10.48550/arxiv.2609.05820","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.05820","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.05820","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.05820","pdf_url":"https://arxiv.org/pdf/2609.05820","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212035784.pdf","grobid_xml":"https://content.openalex.org/works/W7212035784.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W4327810158","https://openalex.org/W4376122773","https://openalex.org/W4386150385","https://openalex.org/W4387163503","https://openalex.org/W4391591662","https://openalex.org/W4392971790","https://openalex.org/W4396782896","https://openalex.org/W4399115803","https://openalex.org/W4400141368","https://openalex.org/W4400531953","https://openalex.org/W4400719267","https://openalex.org/W4401306886","https://openalex.org/W4405253355","https://openalex.org/W4414004064","https://openalex.org/W4415800788","https://openalex.org/W4416037109"],"related_works":["https://openalex.org/W4416394445","https://openalex.org/W4416034518","https://openalex.org/W7221460187","https://openalex.org/W7137929384","https://openalex.org/W7152672525","https://openalex.org/W4416712272","https://openalex.org/W7171523407","https://openalex.org/W7221755332","https://openalex.org/W7084396999","https://openalex.org/W7127428250"],"abstract_inverted_index":{"We":[0,23,48],"study":[1],"adaptive":[2],"routing":[3,102],"of":[4,45,68],"prompts":[5],"to":[6,12,57],"large":[7],"language":[8],"model":[9],"(LLM)":[10],"experts":[11,35],"maximize":[13],"response":[14],"quality":[15],"in":[16,74],"an":[17],"online":[18],"setting":[19,77],"with":[20,30],"limited":[21,108],"feedback.":[22,93,109],"formulate":[24],"it":[25],"as":[26],"a":[27,43,66,90],"bandit":[28,76],"problem":[29],"$K$":[31],"actions":[32],"that":[33,39,51,97],"represent":[34],"and":[36,54],"$d$":[37],"features":[38],"encode":[40],"prompts,":[41],"over":[42],"horizon":[44],"$T$":[46],"rounds.":[47],"propose":[49],"algorithms":[50],"strategically":[52],"select":[53],"observe":[55],"rewards":[56],"minimize":[58],"regret.":[59],"In":[60],"the":[61,75],"full-information":[62],"setting,":[63],"we":[64,78,98],"achieve":[65,79],"regret":[67],"$\\tilde{O}(d":[69,80],"T":[70,81],"/":[71,83],"\\sqrt{m})$,":[72],"while":[73],"\\sqrt{K":[82],"m})$,":[84],"where":[85],"$m":[86],"\\ll":[87],"T$":[88],"is":[89],"budget":[91],"on":[92],"Our":[94],"experiments":[95],"show":[96],"efficiently":[99],"learn":[100],"high-quality":[101],"strategies":[103],"across":[104],"diverse":[105],"LLMs":[106],"from":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-10T00:00:00"}