{"id":"https://openalex.org/W7134166413","doi":"https://doi.org/10.1049/cit2.70108","title":"Multitype Game Optimisation: A Two\u2010Stage Fine\u2010Tuning Framework for Multi\u2011Game Optimisation With Large Language Models","display_name":"Multitype Game Optimisation: A Two\u2010Stage Fine\u2010Tuning Framework for Multi\u2011Game Optimisation With Large Language Models","publication_year":2026,"publication_date":"2026-02-27","ids":{"openalex":"https://openalex.org/W7134166413","doi":"https://doi.org/10.1049/cit2.70108"},"language":"en","primary_location":{"id":"doi:10.1049/cit2.70108","is_oa":true,"landing_page_url":"https://doi.org/10.1049/cit2.70108","pdf_url":null,"source":{"id":"https://openalex.org/S2898415742","display_name":"CAAI Transactions on Intelligence Technology","issn_l":"2468-2322","issn":["2468-2322","2468-6557"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CAAI Transactions on Intelligence Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1049/cit2.70108","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102710318","display_name":"Xiali Li","orcid":"https://orcid.org/0000-0001-7950-6204"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiali Li","raw_affiliation_strings":["Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE Minzu University of China  Beijing China","School of Information and Engineering Minzu University of China  Beijing China"],"raw_orcid":"https://orcid.org/0000-0001-7950-6204","affiliations":[{"raw_affiliation_string":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE Minzu University of China  Beijing China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"School of Information and Engineering Minzu University of China  Beijing China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101369292","display_name":"Jingshi Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingshi Gu","raw_affiliation_strings":["Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE Minzu University of China  Beijing China","School of Information and Engineering Minzu University of China  Beijing China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE Minzu University of China  Beijing China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"School of Information and Engineering Minzu University of China  Beijing China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102630157","display_name":"Feifan He","orcid":"https://orcid.org/0009-0002-3334-2608"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feifan He","raw_affiliation_strings":["Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE Minzu University of China  Beijing China","School of Information and Engineering Minzu University of China  Beijing China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE Minzu University of China  Beijing China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"School of Information and Engineering Minzu University of China  Beijing China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740877","display_name":"Yang Xiao","orcid":"https://orcid.org/0000-0001-6897-5531"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Xiao","raw_affiliation_strings":["Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE Minzu University of China  Beijing China","School of Information and Engineering Minzu University of China  Beijing China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE Minzu University of China  Beijing China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"School of Information and Engineering Minzu University of China  Beijing China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128330858","display_name":"Yuanli Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanli Jia","raw_affiliation_strings":["Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE Minzu University of China  Beijing China","School of Information and Engineering Minzu University of China  Beijing China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE Minzu University of China  Beijing China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"School of Information and Engineering Minzu University of China  Beijing China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086651589","display_name":"Ping Lan","orcid":"https://orcid.org/0009-0009-0367-3896"},"institutions":[{"id":"https://openalex.org/I51622183","display_name":"Shaanxi University of Science and Technology","ror":"https://ror.org/034t3zs45","country_code":"CN","type":"education","lineage":["https://openalex.org/I51622183"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Lan","raw_affiliation_strings":["School of Information Science and Technology Xizang University  Lhasa China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology Xizang University  Lhasa China","institution_ids":["https://openalex.org/I51622183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102710318"],"corresponding_institution_ids":["https://openalex.org/I145897649"],"apc_list":{"value":2600,"currency":"USD","value_usd":2600},"apc_paid":{"value":2600,"currency":"USD","value_usd":2600},"fwci":56.8664,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.99838376,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"11","issue":"3","first_page":"739","last_page":"753"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.7422999739646912,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.7422999739646912,"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/T10731","display_name":"Educational Games and Gamification","score":0.08429999649524689,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.03709999844431877,"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":0.7329999804496765},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5705999732017517},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5403000116348267},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.49970000982284546},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4352000057697296},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4221999943256378},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.3817000091075897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573000192642212},{"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/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5705999732017517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5593000054359436},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5403000116348267},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39570000767707825},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3190999925136566},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C56601403","wikidata":"https://www.wikidata.org/wiki/Q5593673","display_name":"Grammar induction","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1049/cit2.70108","is_oa":true,"landing_page_url":"https://doi.org/10.1049/cit2.70108","pdf_url":null,"source":{"id":"https://openalex.org/S2898415742","display_name":"CAAI Transactions on Intelligence Technology","issn_l":"2468-2322","issn":["2468-2322","2468-6557"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CAAI Transactions on Intelligence Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1049/cit2.70108","is_oa":true,"landing_page_url":"https://doi.org/10.1049/cit2.70108","pdf_url":null,"source":{"id":"https://openalex.org/S2898415742","display_name":"CAAI Transactions on Intelligence Technology","issn_l":"2468-2322","issn":["2468-2322","2468-6557"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CAAI Transactions on Intelligence Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1681167796","display_name":null,"funder_award_id":"62236011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6229712225","display_name":null,"funder_award_id":"62276285","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2257979135","https://openalex.org/W2612780607","https://openalex.org/W2730357202","https://openalex.org/W2761873684","https://openalex.org/W2766447205","https://openalex.org/W2773381986","https://openalex.org/W2902907165","https://openalex.org/W2970741249","https://openalex.org/W3021750196","https://openalex.org/W3098147269","https://openalex.org/W3149440924","https://openalex.org/W3157811306","https://openalex.org/W4226278401","https://openalex.org/W4281663178","https://openalex.org/W4380994417","https://openalex.org/W4385489186","https://openalex.org/W4391307900","https://openalex.org/W4393050579","https://openalex.org/W4399307691","https://openalex.org/W4399458232","https://openalex.org/W4399767534","https://openalex.org/W4400701072","https://openalex.org/W4401880582","https://openalex.org/W4403883066","https://openalex.org/W4410582774","https://openalex.org/W7117326012"],"related_works":[],"abstract_inverted_index":{"ABSTRACT":[0],"Large":[1],"language":[2,11],"models":[3,134],"(LLMs)":[4],"have":[5],"made":[6],"remarkable":[7],"advances":[8],"in":[9,16,36,124,144,163,174],"natural":[10],"processing,":[12],"demonstrating":[13],"great":[14],"potential":[15],"modelling":[17],"structured":[18],"sequences.":[19],"However,":[20],"adapting":[21],"these":[22],"capabilities":[23],"to":[24,34,65,115,140],"machine":[25],"gaming":[26],"tasks":[27,166],"such":[28],"as":[29],"Go":[30],"remains":[31],"challenging":[32],"due":[33],"limitations":[35],"strategy":[37,147,179],"generalisation":[38,150],"and":[39,151,167,177],"optimisation":[40,47],"efficiency.":[41,153],"This":[42,154],"paper":[43],"presents":[44],"multitype":[45],"game":[46,89,125,175],"(MyGO),":[48],"a":[49,76,157,169],"two\u2010stage":[50],"fine\u2010tuning":[51,72,161],"framework":[52],"tailored":[53],"for":[54,160,171],"two\u2010player":[55],"perfect":[56],"information":[57],"board":[58],"games,":[59],"exploring":[60],"the":[61,70,99,117,132],"applicability":[62],"of":[63,119,146],"LLMs":[64,162],"nonlinguistic":[66],"decision\u2010making":[67,165],"domains.":[68],"In":[69,98],"supervised":[71],"stage,":[73,102],"we":[74,103],"propose":[75],"unified":[77],"structural":[78],"encoding":[79],"method,":[80],"action":[81],"semantic":[82],"unit":[83],"(ASU),":[84],"which":[85],"efficiently":[86],"converts":[87],"heterogeneous":[88],"records":[90],"into":[91],"discrete":[92],"token":[93],"sequences":[94],"compatible":[95],"with":[96],"LLMs.":[97],"reinforcement":[100,126],"learning":[101],"design":[104],"TA\u2010PPO":[105],"(token\u2010level":[106],"adaptive":[107],"proximal":[108],"policy":[109],"optimisation),":[110],"an":[111],"enhanced":[112],"PPO\u2010based":[113],"algorithm":[114],"address":[116],"issue":[118],"sparse":[120],"feedback":[121],"commonly":[122],"encountered":[123],"learning.":[127],"Experimental":[128],"results":[129],"demonstrate":[130],"that":[131],"fine\u2010tuned":[133],"achieve":[135],"superior":[136],"or":[137],"comparable":[138],"performance":[139],"traditional":[141],"game\u2010playing":[142],"algorithms":[143],"terms":[145],"quality,":[148],"rule":[149],"inference":[152],"work":[155],"provides":[156],"scalable":[158],"paradigm":[159],"complex":[164],"lays":[168],"foundation":[170],"future":[172],"research":[173],"AI":[176],"generalisable":[178],"optimisation.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":7}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2026-03-09T00:00:00"}