{"id":"https://openalex.org/W4417032030","doi":"https://doi.org/10.1109/comst.2026.3712862","title":"Tutorial on Large Language Model-Enhanced Reinforcement Learning for Wireless Networks","display_name":"Tutorial on Large Language Model-Enhanced Reinforcement Learning for Wireless Networks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417032030","doi":"https://doi.org/10.1109/comst.2026.3712862"},"language":null,"primary_location":{"id":"doi:10.1109/comst.2026.3712862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/comst.2026.3712862","pdf_url":null,"source":{"id":"https://openalex.org/S23688054","display_name":"IEEE Communications Surveys & Tutorials","issn_l":"1553-877X","issn":["1553-877X","2373-745X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Communications Surveys & Tutorials","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.03722","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103255133","display_name":"Lingyi Cai","orcid":"https://orcid.org/0000-0003-2794-8179"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyi Cai","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":"https://orcid.org/0009-0007-8774-2769","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101741812","display_name":"Wenjie Fu","orcid":"https://orcid.org/0009-0004-9879-946X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Fu","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113373614","display_name":"Yuxi Huang","orcid":"https://orcid.org/0009-0004-2094-2481"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxi Huang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049587970","display_name":"Ruichen Zhang","orcid":"https://orcid.org/0000-0002-6859-3645"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ruichen Zhang","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":"https://orcid.org/0000-0002-6859-3645","affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068961034","display_name":"Yinqiu Liu","orcid":"https://orcid.org/0000-0002-6198-3712"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yinqiu Liu","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":"https://orcid.org/0000-0002-6198-3712","affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062761975","display_name":"Jiawen Kang","orcid":"https://orcid.org/0000-0002-8218-3490"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawen Kang","raw_affiliation_strings":["Guangdong University of Technology"],"raw_orcid":"https://orcid.org/0000-0002-8218-3490","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005327587","display_name":"Zehui Xiong","orcid":"https://orcid.org/0000-0002-4440-941X"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zehui Xiong","raw_affiliation_strings":["Queen\u2019s University Belfast"],"raw_orcid":"https://orcid.org/0000-0002-4440-941X","affiliations":[{"raw_affiliation_string":"Queen\u2019s University Belfast","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100678341","display_name":"Tao Jiang","orcid":"https://orcid.org/0000-0002-8482-1046"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Jiang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":"https://orcid.org/0000-0002-8482-1046","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733413","display_name":"Xianbin Wang","orcid":"https://orcid.org/0000-0003-4890-0748"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xianbin Wang","raw_affiliation_strings":["Western University"],"raw_orcid":"https://orcid.org/0000-0003-4890-0748","affiliations":[{"raw_affiliation_string":"Western University","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080122431","display_name":"Shiwen Mao","orcid":"https://orcid.org/0000-0002-7052-0007"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiwen Mao","raw_affiliation_strings":["Auburn University"],"raw_orcid":"https://orcid.org/0000-0002-7052-0007","affiliations":[{"raw_affiliation_string":"Auburn University","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100773343","display_name":"Xuemin Shen","orcid":"https://orcid.org/0000-0002-4140-287X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xuemin Shen","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":"https://orcid.org/0000-0002-4140-287X","affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01913913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"6665","last_page":"6693"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.14339999854564667,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.14339999854564667,"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/T13553","display_name":"Age of Information Optimization","score":0.10050000250339508,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13918","display_name":"Advanced Data and IoT Technologies","score":0.09369999915361404,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7631999850273132},{"id":"https://openalex.org/keywords/transformative-learning","display_name":"Transformative learning","score":0.5891000032424927},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.5217999815940857},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.5200999975204468},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.49950000643730164}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7631999850273132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7228000164031982},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.5891000032424927},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.5217999815940857},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38589999079704285},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34389999508857727},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2870999872684479}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/comst.2026.3712862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/comst.2026.3712862","pdf_url":null,"source":{"id":"https://openalex.org/S23688054","display_name":"IEEE Communications Surveys & Tutorials","issn_l":"1553-877X","issn":["1553-877X","2373-745X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Communications Surveys & Tutorials","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2512.03722","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.03722","pdf_url":"https://arxiv.org/pdf/2512.03722","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,"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.2512.03722","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.03722","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.03722","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.03722","pdf_url":"https://arxiv.org/pdf/2512.03722","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,"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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417032030.pdf","grobid_xml":"https://content.openalex.org/works/W4417032030.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3],"shown":[4],"remarkable":[5],"success":[6],"in":[7,16,25,33,53,139,169],"enabling":[8],"adaptive":[9],"and":[10,30,58,102,135,145,162],"data-driven":[11],"optimization":[12],"for":[13,80,159],"various":[14],"applications":[15],"wireless":[17,35,81,170],"networks.":[18,82,148,171],"However,":[19],"classical":[20,68],"RL":[21,79,120,138,161],"suffers":[22],"from":[23],"limitations":[24],"generalization,":[26,55],"learning":[27],"feedback,":[28],"interpretability,":[29],"sample":[31],"efficiency":[32],"dynamic":[34],"environments.":[36],"Large":[37],"Language":[38],"Models":[39],"(LLMs)":[40],"have":[41,62],"emerged":[42],"as":[43,73],"a":[44,74,85,125,153],"transformative":[45],"Artificial":[46],"Intelligence":[47],"(AI)":[48],"paradigm":[49],"with":[50,152],"exceptional":[51],"capabilities":[52],"knowledge":[54],"contextual":[56],"reasoning,":[57],"interactive":[59],"generation,":[60],"which":[61],"demonstrated":[63],"strong":[64],"potential":[65,156],"to":[66,87,130,133],"enhance":[67],"RL.":[69],"This":[70],"paper":[71],"serves":[72],"comprehensive":[75],"tutorial":[76],"on":[77,155],"LLM-enhanced":[78,137,160],"We":[83],"propose":[84],"taxonomy":[86],"categorize":[88],"the":[89,119],"roles":[90],"of":[91,113,118,127],"LLMs":[92,114],"into":[93,165],"four":[94],"critical":[95],"functions:":[96],"state":[97],"perceiver,":[98],"reward":[99],"designer,":[100],"decision-maker,":[101],"generator.":[103],"Then,":[104],"we":[105,123,150],"review":[106],"existing":[107],"studies":[108,129],"exploring":[109],"how":[110,132],"each":[111],"role":[112],"enhances":[115],"different":[116],"stages":[117],"pipeline.":[121],"Moreover,":[122],"provide":[124],"series":[126],"case":[128],"illustrate":[131],"design":[134],"apply":[136],"low-altitude":[140],"economy":[141],"networking,":[142],"vehicular":[143],"networks,":[144],"space-air-ground":[146],"integrated":[147],"Finally,":[149],"conclude":[151],"discussion":[154],"future":[157,167],"directions":[158],"offer":[163],"insights":[164],"its":[166],"development":[168]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-12-05T00:00:00"}