{"id":"https://openalex.org/W4415378015","doi":"https://doi.org/10.1109/icdl63968.2025.11204357","title":"Fast or Slow: Adaptive Decision-Making in Reinforcement Learning with Pre-Trained LLMs","display_name":"Fast or Slow: Adaptive Decision-Making in Reinforcement Learning with Pre-Trained LLMs","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4415378015","doi":"https://doi.org/10.1109/icdl63968.2025.11204357"},"language":null,"primary_location":{"id":"doi:10.1109/icdl63968.2025.11204357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035552079","display_name":"Katrine Linnea Nerg\u00e5rd","orcid":"https://orcid.org/0000-0002-9681-0088"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Katrine Linnea Nerg\u00e5rd","raw_affiliation_strings":["University of Oslo,Department of Informatics,Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo,Department of Informatics,Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071893221","display_name":"Kai Olav Ellefsen","orcid":"https://orcid.org/0000-0003-2466-2319"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Kai Olav Ellefsen","raw_affiliation_strings":["University of Oslo,Department of Informatics,Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo,Department of Informatics,Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071144214","display_name":"Jim T\u00f8rresen","orcid":"https://orcid.org/0000-0003-0556-0288"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Jim Torresen","raw_affiliation_strings":["University of Oslo,Department of Informatics,Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo,Department of Informatics,Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184942183"],"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":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14351","display_name":"Statistical and Computational Modeling","score":0.5184000134468079,"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/T14351","display_name":"Statistical and Computational Modeling","score":0.5184000134468079,"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/T10260","display_name":"Software Engineering Research","score":0.5149000287055969,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.5059999823570251,"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":0.7754999995231628},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6651999950408936},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5442000031471252},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.42730000615119934},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.3513999879360199},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3391000032424927},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.33379998803138733}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7754999995231628},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6651999950408936},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5442000031471252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5300999879837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45419999957084656},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.35989999771118164},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.33379998803138733},{"id":"https://openalex.org/C68784500","wikidata":"https://www.wikidata.org/wiki/Q1570691","display_name":"Adaptive behavior","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30630001425743103},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26420000195503235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25859999656677246},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdl63968.2025.11204357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2964915587","https://openalex.org/W3174239553","https://openalex.org/W4312436892"],"related_works":[],"abstract_inverted_index":{"This":[0,118],"study":[1],"investigates":[2],"the":[3,21,32,75,81,102,115],"use":[4],"of":[5,35,109,124],"Large":[6],"Language":[7],"Models":[8],"(LLMs)":[9],"in":[10,87,126],"Reinforcement":[11],"Learning":[12],"(RL)":[13],"to":[14,23,27,43,60,78,107],"mimic":[15],"human":[16],"adaptive":[17],"reasoning,":[18],"and":[19,50],"hence":[20],"ability":[22,77],"adjust":[24],"cognitive":[25],"effort":[26],"task":[28],"complexity.":[29],"Inspired":[30],"by":[31],"dual-system":[33],"theory":[34],"cognition,":[36],"our":[37],"approach":[38],"employs":[39],"a":[40,88,110,121],"pre-trained":[41],"LLM":[42],"guide":[44],"an":[45],"RL":[46],"agent":[47,112],"between":[48],"\u201cfast\u201d":[49],"\u201cslow\u201d":[51],"thinking":[52],"modes.":[53],"These":[54],"modes":[55],"are":[56],"policies":[57],"that":[58,101,108],"correspond":[59],"either":[61],"rapid,":[62],"intuitive":[63],"responses":[64],"or":[65,96],"more":[66,135],"calculated,":[67],"deliberate":[68],"actions.":[69],"Our":[70],"main":[71],"contribution":[72],"is":[73,105],"demonstrating":[74],"LLM\u2019s":[76,103],"dynamically":[79],"select":[80],"appropriate":[82],"mode":[83],"for":[84,114,134],"varying":[85],"situations":[86],"custom":[89],"grid-world":[90],"environment,":[91],"without":[92],"requiring":[93],"additional":[94],"training":[95],"fine-tuning.":[97],"Moreover,":[98],"we":[99],"demonstrate":[100],"performance":[104],"comparable":[106],"Q-learning":[111],"trained":[113],"same":[116],"purpose.":[117],"research":[119],"presents":[120],"proof-of-concept":[122],"integration":[123],"LLMs":[125],"RL,":[127],"offering":[128],"preliminary":[129],"insights":[130],"into":[131],"their":[132],"potential":[133],"complex":[136],"decision-making.":[137]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-21T00:00:00"}