{"id":"https://openalex.org/W7165370395","doi":"https://doi.org/10.48550/arxiv.2606.19750","title":"Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models","display_name":"Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W7165370395","doi":"https://doi.org/10.48550/arxiv.2606.19750"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.19750","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19750","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.2606.19750","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112879299","display_name":"Darrien McKenzie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McKenzie, Darrien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139002628","display_name":"Nicklas Hansen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hansen, Nicklas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139020444","display_name":"Xiaolong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaolong","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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.12409999966621399,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.12409999966621399,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.08749999850988388,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.08330000191926956,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/operationalization","display_name":"Operationalization","score":0.5766000151634216},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5462999939918518},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5196999907493591},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4490000009536743},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4480000138282776},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4348999857902527},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.4189000129699707},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4050000011920929},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.3912999927997589}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6291000247001648},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6051999926567078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5838000178337097},{"id":"https://openalex.org/C9354725","wikidata":"https://www.wikidata.org/wiki/Q286017","display_name":"Operationalization","level":2,"score":0.5766000151634216},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5462999939918518},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4480000138282776},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4348999857902527},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.4189000129699707},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3912999927997589},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C101112237","wikidata":"https://www.wikidata.org/wiki/Q4874481","display_name":"Bayesian statistics","level":4,"score":0.3716999888420105},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2969000041484833},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.2694999873638153},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.19750","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19750","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.2606.19750","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19750","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/8","score":0.43942347168922424,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,31,90,120],"(RL)":[2],"is":[3,155],"a":[4,43,68,106,113],"central":[5],"approach":[6],"for":[7,157],"improving":[8],"reasoning":[9],"capabilities":[10],"in":[11],"large":[12],"language":[13],"models":[14],"(LLMs),":[15],"where":[16],"training":[17],"efficiency":[18],"depends":[19],"critically":[20],"on":[21],"how":[22,89],"problems":[23,75,111],"are":[24,76],"sampled":[25],"during":[26],"optimization.":[27],"Existing":[28],"adaptive":[29],"curriculum":[30],"methods":[32],"typically":[33],"prioritize":[34],"prompts":[35],"of":[36,56,140,164],"intermediate":[37],"difficulty,":[38],"treating":[39],"problem":[40,46,65,71,170],"selection":[41],"as":[42,67],"standard":[44],"bandit":[45,70],"with":[47,72],"independent":[48],"arms":[49],"and":[50,84,117,144,167],"overlooking":[51],"the":[52,57,79,141,162],"structured,":[53],"heterogeneous":[54],"nature":[55],"task":[58,115,142],"space.":[59,95],"In":[60],"this":[61,98],"work,":[62],"we":[63,100,125],"frame":[64],"sampling":[66,85,129],"manifold-structured":[69],"endogenous":[73],"non-stationarity:":[74],"related":[77],"through":[78],"model's":[80],"latent":[81],"representation":[82],"space,":[83],"decisions":[86],"can":[87],"steer":[88],"signals":[91],"evolve":[92],"across":[93],"that":[94,109,127,151],"To":[96],"operationalize":[97],"perspective,":[99],"introduce":[101],"Bayesian":[102,119],"Manifold":[103],"Curriculum":[104],"(BMC),":[105],"structure-aware":[107],"framework":[108],"organizes":[110],"into":[112,169],"hierarchical":[114],"tree":[116],"applies":[118],"to":[121],"guide":[122],"sampling.":[123,171],"Empirically,":[124],"find":[126],"different":[128],"strategies":[130],"induce":[131],"non-trivial":[132],"tradeoffs":[133],"between":[134],"productivity":[135],"(learning":[136],"signal),":[137],"diversity":[138],"(coverage":[139],"manifold),":[143],"utility":[145],"(evaluation":[146],"relevance).":[147],"These":[148],"results":[149],"show":[150],"prioritizing":[152],"difficulty":[153],"alone":[154],"insufficient":[156],"strong":[158],"downstream":[159],"performance,":[160],"highlighting":[161],"importance":[163],"incorporating":[165],"structure":[166],"type-awareness":[168]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-20T00:00:00"}