{"id":"https://openalex.org/W4415427987","doi":"https://doi.org/10.3233/faia251344","title":"Disentangling Exploration of Large Language Models by Optimal Exploitation","display_name":"Disentangling Exploration of Large Language Models by Optimal Exploitation","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415427987","doi":"https://doi.org/10.3233/faia251344"},"language":null,"primary_location":{"id":"doi:10.3233/faia251344","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251344","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251344","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114241183","display_name":"Tim Grams","orcid":null},"institutions":[{"id":"https://openalex.org/I43980791","display_name":"Clausthal University of Technology","ror":"https://ror.org/04qb8nc58","country_code":"DE","type":"education","lineage":["https://openalex.org/I43980791"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tim Grams","raw_affiliation_strings":["Technical University of Clausthal"],"affiliations":[{"raw_affiliation_string":"Technical University of Clausthal","institution_ids":["https://openalex.org/I43980791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041758340","display_name":"Patrick Betz","orcid":"https://orcid.org/0009-0003-4948-3912"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Patrick Betz","raw_affiliation_strings":["University of Mannheim"],"affiliations":[{"raw_affiliation_string":"University of Mannheim","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022929385","display_name":"Sascha Marton","orcid":"https://orcid.org/0000-0001-8151-9223"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sascha Marton","raw_affiliation_strings":["University of Mannheim"],"affiliations":[{"raw_affiliation_string":"University of Mannheim","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048318892","display_name":"Stefan L\u00fcdtke","orcid":"https://orcid.org/0000-0002-7888-9175"},"institutions":[{"id":"https://openalex.org/I4665924","display_name":"University of Rostock","ror":"https://ror.org/03zdwsf69","country_code":"DE","type":"education","lineage":["https://openalex.org/I4665924"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan L\u00fcdtke","raw_affiliation_strings":["University of Rostock"],"affiliations":[{"raw_affiliation_string":"University of Rostock","institution_ids":["https://openalex.org/I4665924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020967690","display_name":"Christian Bartelt","orcid":"https://orcid.org/0000-0003-0426-6714"},"institutions":[{"id":"https://openalex.org/I43980791","display_name":"Clausthal University of Technology","ror":"https://ror.org/04qb8nc58","country_code":"DE","type":"education","lineage":["https://openalex.org/I43980791"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Bartelt","raw_affiliation_strings":["Technical University of Clausthal"],"affiliations":[{"raw_affiliation_string":"Technical University of Clausthal","institution_ids":["https://openalex.org/I43980791"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114241183"],"corresponding_institution_ids":["https://openalex.org/I43980791"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50354027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.8144000172615051,"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":0.8144000172615051,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6942999958992004,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.652400016784668},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5314000248908997},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4498000144958496},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.421099990606308},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.38029998540878296},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.3264999985694885},{"id":"https://openalex.org/keywords/complete-information","display_name":"Complete information","score":0.30820000171661377}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.652400016784668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6395000219345093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5325000286102295},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3901999890804291},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C60044698","wikidata":"https://www.wikidata.org/wiki/Q1283324","display_name":"Refining (metallurgy)","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C3018260909","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory analysis","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251344","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251344","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251344","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251344","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"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":{"Exploration":[0],"is":[1,55,95],"a":[2,23,59,100,123],"crucial":[3],"skill":[4],"for":[5,58,126],"in-context":[6],"reinforcement":[7],"learning":[8],"in":[9,116,129],"unknown":[10],"environments.":[11],"However,":[12],"it":[13],"remains":[14],"unclear":[15],"if":[16],"large":[17],"language":[18],"models":[19,82],"can":[20,111],"effectively":[21],"explore":[22,88],"partially":[24],"hidden":[25],"state":[26,90],"space.":[27],"This":[28],"work":[29],"isolates":[30],"exploration":[31,69,94,104],"as":[32],"the":[33,75,89],"sole":[34],"objective,":[35],"tasking":[36],"an":[37],"agent":[38,53],"with":[39,80],"gathering":[40],"information":[41],"that":[42,51,84],"enhances":[43],"future":[44],"returns.":[45],"Within":[46],"this":[47],"framework,":[48],"we":[49,63,98],"argue":[50],"measuring":[52],"returns":[54],"not":[56],"sufficient":[57],"fair":[60],"evaluation.":[61],"Hence,":[62],"decompose":[64],"missing":[65],"rewards":[66],"into":[67,114],"their":[68],"and":[70,92,106],"exploitation":[71],"components":[72],"based":[73],"on":[74],"optimal":[76],"achievable":[77],"return.":[78],"Experiments":[79],"various":[81],"reveal":[83],"most":[85],"struggle":[86],"to":[87],"space,":[91],"weak":[93],"insufficient.":[96],"Nevertheless,":[97],"found":[99],"positive":[101],"correlation":[102],"between":[103],"performance":[105,128],"reasoning":[107],"capabilities.":[108],"Our":[109],"decomposition":[110],"provide":[112],"insights":[113],"differences":[115],"behaviors":[117],"driven":[118],"by":[119],"prompt":[120],"engineering,":[121],"offering":[122],"valuable":[124],"tool":[125],"refining":[127],"exploratory":[130],"tasks.":[131]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}