{"id":"https://openalex.org/W7130541052","doi":"https://doi.org/10.1109/ictc66702.2025.11387958","title":"Forging Agentic AI: A Comprehensive Survey on the Symbiotic Convergence of Large Language Models and Reinforcement Learning","display_name":"Forging Agentic AI: A Comprehensive Survey on the Symbiotic Convergence of Large Language Models and Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7130541052","doi":"https://doi.org/10.1109/ictc66702.2025.11387958"},"language":null,"primary_location":{"id":"doi:10.1109/ictc66702.2025.11387958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11387958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","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/A5100362664","display_name":"Minsoo Kim","orcid":"https://orcid.org/0000-0002-4137-4610"},"institutions":[{"id":"https://openalex.org/I4210120602","display_name":"Advanced Institute of Convergence Technology","ror":"https://ror.org/01w62yz22","country_code":"KR","type":"facility","lineage":["https://openalex.org/I139264467","https://openalex.org/I4210120602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsoo Kim","raw_affiliation_strings":["Ajou Univerity,Dept. Aritificial Intelligence Convergence Network,Suwon,South Korea,16499"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ajou Univerity,Dept. Aritificial Intelligence Convergence Network,Suwon,South Korea,16499","institution_ids":["https://openalex.org/I4210120602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041027404","display_name":"Junsu Kim","orcid":"https://orcid.org/0000-0001-9583-7978"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Joongheon Kim","raw_affiliation_strings":["Korea University,Dept. Electrical and Computer Engineering,Seoul,South Korea,02841"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Dept. Electrical and Computer Engineering,Seoul,South Korea,02841","institution_ids":["https://openalex.org/I197347611","https://openalex.org/I4210161052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039532704","display_name":"Soyi Jung","orcid":"https://orcid.org/0000-0001-8435-0646"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soyi Jung","raw_affiliation_strings":["Ajou University,Dept. Electrical and Computer Engineering,Suwon,South Korea,16499"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ajou University,Dept. Electrical and Computer Engineering,Suwon,South Korea,16499","institution_ids":["https://openalex.org/I57664883"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":"618","last_page":"623"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.22609999775886536,"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":0.22609999775886536,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.18889999389648438,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.05510000139474869,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7329999804496765},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.498199999332428},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4528000056743622},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4250999987125397}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7329999804496765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5214999914169312},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36800000071525574},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3668000102043152},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.26829999685287476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc66702.2025.11387958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11387958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2168405694","https://openalex.org/W2169209873","https://openalex.org/W2257979135","https://openalex.org/W3133541004","https://openalex.org/W4379382600","https://openalex.org/W4392490033","https://openalex.org/W4395017309","https://openalex.org/W4401980055","https://openalex.org/W4408324122","https://openalex.org/W4409347437","https://openalex.org/W4411019644","https://openalex.org/W4411086320","https://openalex.org/W4411179911","https://openalex.org/W4414050442","https://openalex.org/W4415798571"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,61],"(RL)":[2],"has":[3],"shown":[4],"remarkable":[5],"success":[6],"in":[7,31,66,121],"solving":[8],"complex":[9],"decision-making":[10],"problems;":[11],"however,":[12],"it":[13],"still":[14],"suffers":[15],"from":[16],"fundamental":[17],"limitations":[18],"such":[19],"as":[20],"low":[21],"sample":[22],"efficiency,":[23],"sparse":[24],"rewards,":[25],"and":[26,76,81,90,98,109,119,125],"poor":[27],"generalization.":[28,82],"Recent":[29],"advances":[30],"large":[32],"language":[33],"models":[34],"(LLMs)":[35],"have":[36],"introduced":[37],"new":[38],"possibilities":[39],"for":[40],"overcoming":[41],"these":[42],"challenges":[43],"by":[44],"enhancing":[45],"multiple":[46],"components":[47],"of":[48,58],"the":[49,64,114],"RL":[50,120],"pipeline.":[51],"This":[52],"survey":[53],"provides":[54],"a":[55],"comprehensive":[56],"overview":[57],"LLM-augmented":[59],"reinforcement":[60],"(LLM-RL),":[62],"highlighting":[63],"ways":[65],"which":[67],"LLMs":[68,118],"contribute":[69],"to":[70,112],"reward":[71],"design,":[72],"exploration,":[73],"planning,":[74],"state":[75],"action":[77],"representation,":[78],"policy":[79],"learning,":[80],"We":[83],"categorize":[84],"integration":[85],"strategies,":[86],"analyze":[87],"representative":[88],"frameworks,":[89],"discuss":[91,103],"key":[92],"application":[93],"areas":[94],"including":[95],"robotics,":[96],"gaming,":[97],"virtual":[99],"environments.":[100],"Finally,":[101],"we":[102],"current":[104],"limitations,":[105],"open":[106],"research":[107],"challenges,":[108],"future":[110],"directions":[111],"highlight":[113],"potential":[115],"synergy":[116],"between":[117],"building":[122],"more":[123],"general":[124],"adaptable":[126],"autonomous":[127],"agents.":[128]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}