{"id":"https://openalex.org/W4415658650","doi":"https://doi.org/10.1007/s11633-025-1547-3","title":"Theory of Mind Inspired Large Reasoning Language Model Improved Multi-agent Reinforcement Learning Algorithm for Robust and Adaptive Partner Modelling","display_name":"Theory of Mind Inspired Large Reasoning Language Model Improved Multi-agent Reinforcement Learning Algorithm for Robust and Adaptive Partner Modelling","publication_year":2025,"publication_date":"2025-10-29","ids":{"openalex":"https://openalex.org/W4415658650","doi":"https://doi.org/10.1007/s11633-025-1547-3"},"language":"en","primary_location":{"id":"doi:10.1007/s11633-025-1547-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11633-025-1547-3","pdf_url":null,"source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"type":"article","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/A5056702546","display_name":"Xiyun Li","orcid":"https://orcid.org/0009-0001-9517-7030"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiyun Li","raw_affiliation_strings":["School of Future Technology, University of Chinese Academy of Sciences, Beijing, 101408, China","The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"School of Future Technology, University of Chinese Academy of Sciences, Beijing, 101408, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027787838","display_name":"Tielin Zhang","orcid":"https://orcid.org/0000-0002-5111-9891"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tielin Zhang","raw_affiliation_strings":["Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, 200031, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, 200031, China","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047329586","display_name":"Chenghao Liu","orcid":"https://orcid.org/0000-0001-7923-6806"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenghao Liu","raw_affiliation_strings":["The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004363895","display_name":"Shuang Xu","orcid":"https://orcid.org/0000-0003-3576-6914"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Xu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","School of Future Technology, University of Chinese Academy of Sciences, Beijing, 101408, China","The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Future Technology, University of Chinese Academy of Sciences, Beijing, 101408, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056702546"],"corresponding_institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3656441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"6","first_page":"1088","last_page":"1101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.2736999988555908,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.2736999988555908,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09839999675750732,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.05979999899864197,"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/semantic-reasoner","display_name":"Semantic reasoner","score":0.6948999762535095},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6057999730110168},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.541100025177002},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5149000287055969},{"id":"https://openalex.org/keywords/psychology-of-reasoning","display_name":"Psychology of reasoning","score":0.48899999260902405},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.47130000591278076},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.39989998936653137},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3824999928474426}],"concepts":[{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.6948999762535095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6509000062942505},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6057999730110168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.599399983882904},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5149000287055969},{"id":"https://openalex.org/C183521366","wikidata":"https://www.wikidata.org/wiki/Q7256422","display_name":"Psychology of reasoning","level":4,"score":0.48899999260902405},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.388700008392334},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3635999858379364},{"id":"https://openalex.org/C2779560602","wikidata":"https://www.wikidata.org/wiki/Q639219","display_name":"Theory of mind","level":3,"score":0.32350000739097595},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C68784500","wikidata":"https://www.wikidata.org/wiki/Q1570691","display_name":"Adaptive behavior","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C107848011","wikidata":"https://www.wikidata.org/wiki/Q4680756","display_name":"Adaptive reasoning","level":4,"score":0.3021000027656555},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C166998942","wikidata":"https://www.wikidata.org/wiki/Q16969238","display_name":"Interactor","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11633-025-1547-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11633-025-1547-3","pdf_url":null,"source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1965881519","https://openalex.org/W1969918023","https://openalex.org/W1978165201","https://openalex.org/W1986542309","https://openalex.org/W1990955460","https://openalex.org/W2010931158","https://openalex.org/W2019963249","https://openalex.org/W2035727518","https://openalex.org/W2041336675","https://openalex.org/W2044475205","https://openalex.org/W2052610531","https://openalex.org/W2055311105","https://openalex.org/W2071256705","https://openalex.org/W2075577262","https://openalex.org/W2106053034","https://openalex.org/W2107866216","https://openalex.org/W2113669408","https://openalex.org/W2119224589","https://openalex.org/W2124722681","https://openalex.org/W2136162329","https://openalex.org/W2136366217","https://openalex.org/W2140713996","https://openalex.org/W2140757037","https://openalex.org/W2151137320","https://openalex.org/W2158211182","https://openalex.org/W2166337720","https://openalex.org/W2256669593","https://openalex.org/W2407554987","https://openalex.org/W2617547828","https://openalex.org/W2758442112","https://openalex.org/W2946045694","https://openalex.org/W2963658727","https://openalex.org/W2982316857","https://openalex.org/W3082884068","https://openalex.org/W3098605233","https://openalex.org/W4285392457","https://openalex.org/W4312458615","https://openalex.org/W4362590704","https://openalex.org/W4383373730","https://openalex.org/W4385571775","https://openalex.org/W4389523957","https://openalex.org/W4389991792","https://openalex.org/W4393065402","https://openalex.org/W4402351273"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-28T02:08:47.144824","created_date":"2025-10-29T00:00:00"}
