{"id":"https://openalex.org/W4414359266","doi":"https://doi.org/10.24963/ijcai.2025/1198","title":"Grounding Open-Domain Knowledge from LLMs to Real-World Reinforcement Learning Tasks: A Survey","display_name":"Grounding Open-Domain Knowledge from LLMs to Real-World Reinforcement Learning Tasks: A Survey","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359266","doi":"https://doi.org/10.24963/ijcai.2025/1198"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1198","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5101943775","display_name":"Haiyan Yin","orcid":"https://orcid.org/0000-0001-8796-3448"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haiyan Yin","raw_affiliation_strings":["CFAR and IHPC, Agency for Science, Technology and Research (A*STAR), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CFAR and IHPC, Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113233267","display_name":"Hangwei Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hangwei Qian","raw_affiliation_strings":["CFAR and IHPC, Agency for Science, Technology and Research (A*STAR), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CFAR and IHPC, Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071855990","display_name":"Yaxin Shi","orcid":"https://orcid.org/0000-0002-0485-4842"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yaxin Shi","raw_affiliation_strings":["CFAR and IHPC, Agency for Science, Technology and Research (A*STAR), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CFAR and IHPC, Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021751767","display_name":"Ivor W. Tsang","orcid":"https://orcid.org/0000-0001-8095-4637"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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":"Ivor Tsang","raw_affiliation_strings":["CFAR and IHPC, Agency for Science, Technology and Research (A*STAR), Singapore","College of Computing and Data Science, Nanyang Technological University (NTU), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CFAR and IHPC, Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068243197","display_name":"Yew-Soon Ong","orcid":"https://orcid.org/0000-0002-4480-169X"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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":"Yew-Soon Ong","raw_affiliation_strings":["CFAR and IHPC, Agency for Science, Technology and Research (A*STAR), Singapore","College of Computing and Data Science, Nanyang Technological University (NTU), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CFAR and IHPC, Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10797","last_page":"10806"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9280999898910522,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9280999898910522,"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/transformative-learning","display_name":"Transformative learning","score":0.586899995803833},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.51910001039505},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5174999833106995},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.44929999113082886},{"id":"https://openalex.org/keywords/mirroring","display_name":"Mirroring","score":0.4221000075340271},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.375900000333786},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.3095000088214874}],"concepts":[{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.586899995803833},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44859999418258667},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.4345000088214874},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3596999943256378},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3025999963283539},{"id":"https://openalex.org/C514011633","wikidata":"https://www.wikidata.org/wiki/Q1428168","display_name":"Traditional knowledge","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C79416737","wikidata":"https://www.wikidata.org/wiki/Q2305519","display_name":"Social learning","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2840999960899353},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/1198","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"Grounding":[0,41],"open-domain":[1,59,156],"knowledge":[2,60,116,157],"from":[3],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"into":[8,53],"real-world":[9,73,126],"reinforcement":[10],"learning":[11],"(RL)":[12],"tasks":[13,102],"represents":[14],"a":[15,43],"transformative":[16],"frontier":[17],"in":[18,31],"developing":[19],"intelligent":[20],"agents":[21,137],"capable":[22],"of":[23,90,114,122,135,150],"advanced":[24],"reasoning,":[25],"adaptive":[26,159],"planning,":[27],"and":[28,61,69,86,94,118,125],"robust":[29],"decision-making":[30],"dynamic":[32],"environments.":[33,75],"In":[34],"this":[35],"paper,":[36],"we":[37],"introduce":[38],"the":[39,65,84,120,133,148],"LLM-RL":[40,136],"Taxonomy,":[42],"systematic":[44],"framework":[45],"that":[46,97,154],"categorizes":[47],"emerging":[48],"methods":[49],"for":[50,103,138,146],"integrating":[51],"LLMs":[52,91,99],"RL":[54,74,152],"systems":[55,153],"by":[56],"bridging":[57],"their":[58],"reasoning":[62],"capabilities":[63,89],"with":[64,158],"task-specific":[66],"dynamics,":[67],"constraints,":[68],"objectives":[70],"inherent":[71],"to":[72,100],"This":[76],"taxonomy":[77],"encompasses":[78],"both":[79],"training-free":[80],"approaches,":[81],"which":[82],"leverage":[83],"zero-shot":[85],"few-shot":[87],"generalization":[88],"without":[92],"fine-tuning,":[93],"fine-tuning":[95],"paradigms":[96],"adapt":[98],"environment-specific":[101],"improved":[104],"performance.":[105],"We":[106],"critically":[107],"analyze":[108],"these":[109],"methodologies,":[110],"highlight":[111],"practical":[112],"examples":[113],"effective":[115],"grounding,":[117],"examine":[119],"challenges":[121],"alignment,":[123],"generalization,":[124],"deployment.":[127],"Our":[128],"work":[129],"not":[130],"only":[131],"illustrates":[132],"potential":[134],"enhanced":[139],"decision-making,":[140],"but":[141],"also":[142],"offers":[143],"actionable":[144],"insights":[145],"advancing":[147],"design":[149],"next-generation":[151],"integrate":[155],"learning.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}