{"id":"https://openalex.org/W4415538124","doi":"https://doi.org/10.1145/3746027.3755752","title":"MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind","display_name":"MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538124","doi":"https://doi.org/10.1145/3746027.3755752"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":null,"display_name":"Zheng Zhang","orcid":"https://orcid.org/0009-0001-6227-1987"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-6227-1987","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079374143","display_name":"N. Y. Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nuoqian Xiao","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-3392-8778","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027750524","display_name":"Qi Chai","orcid":"https://orcid.org/0009-0009-3717-9482"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Chai","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-3717-9482","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073681676","display_name":"Deheng Ye","orcid":"https://orcid.org/0000-0002-1754-1837"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deheng Ye","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1754-1837","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100446112","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-3086-3128"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3086-3128","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"5824","last_page":"5833"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9965000152587891,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9965000152587891,"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/T12128","display_name":"AI in Service Interactions","score":0.9894000291824341,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9868000149726868,"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/deception","display_name":"Deception","score":0.6266000270843506},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5424000024795532},{"id":"https://openalex.org/keywords/theory-of-mind","display_name":"Theory of mind","score":0.527899980545044},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.3691999912261963},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.35519999265670776},{"id":"https://openalex.org/keywords/intelligent-agent","display_name":"Intelligent agent","score":0.34869998693466187},{"id":"https://openalex.org/keywords/nonverbal-communication","display_name":"Nonverbal communication","score":0.31850001215934753},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.296999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6816999912261963},{"id":"https://openalex.org/C2779267917","wikidata":"https://www.wikidata.org/wiki/Q170028","display_name":"Deception","level":2,"score":0.6266000270843506},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C2779560602","wikidata":"https://www.wikidata.org/wiki/Q639219","display_name":"Theory of mind","level":3,"score":0.527899980545044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43529999256134033},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3336000144481659},{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C2776802673","wikidata":"https://www.wikidata.org/wiki/Q1548396","display_name":"Relevance theory","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C86658582","wikidata":"https://www.wikidata.org/wiki/Q1432778","display_name":"Social cognition","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26269999146461487},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.257999986410141},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":16,"referenced_works":["https://openalex.org/W2151516755","https://openalex.org/W2559780724","https://openalex.org/W2930317805","https://openalex.org/W3022553186","https://openalex.org/W3160674997","https://openalex.org/W3200664512","https://openalex.org/W4385570416","https://openalex.org/W4385570693","https://openalex.org/W4389009528","https://openalex.org/W4402670355","https://openalex.org/W4402727235","https://openalex.org/W4402753835","https://openalex.org/W4403713271","https://openalex.org/W4404783650","https://openalex.org/W4408032258","https://openalex.org/W4408352910"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Model":[2],"(LLM)":[3],"agents":[4,53,171],"have":[5],"demonstrated":[6],"impressive":[7],"capabilities":[8],"in":[9,147,161],"social":[10,20,175],"deduction":[11],"games":[12],"(SDGs)":[13],"like":[14],"Werewolf,":[15],"where":[16],"strategic":[17],"reasoning":[18,176],"and":[19,40,84,100,151],"deception":[21],"are":[22],"essential.":[23],"However,":[24],"current":[25],"approaches":[26],"remain":[27],"limited":[28],"to":[29,48,114],"textual":[30],"information,":[31],"ignoring":[32],"crucial":[33],"multimodal":[34,91,178],"cues":[35],"such":[36],"as":[37,81],"facial":[38,98],"expressions":[39,99],"tone":[41],"of":[42,110,173],"voice":[43],"that":[44,138],"humans":[45],"naturally":[46],"use":[47,75],"communicate.":[49],"Moreover,":[50],"existing":[51],"SDG":[52,94],"primarily":[54],"focus":[55],"on":[56],"inferring":[57],"other":[58],"players'":[59],"identities":[60],"without":[61],"modeling":[62],"how":[63],"others":[64],"perceive":[65],"themselves":[66],"or":[67],"fellow":[68],"players.":[69],"To":[70],"address":[71],"these":[72],"limitations,":[73],"we":[74,156],"One":[76],"Night":[77],"Ultimate":[78],"Werewolf":[79],"(ONUW)":[80],"a":[82,108,166],"testbed":[83],"present":[85],"MultiMind,":[86],"the":[87],"first":[88],"framework":[89],"integrating":[90],"information":[92],"into":[93],"agents.":[95],"MultiMind":[96],"processes":[97],"vocal":[101],"tones":[102],"alongside":[103],"verbal":[104],"content,":[105],"while":[106],"employing":[107],"Theory":[109],"Mind":[111],"(ToM)":[112],"model":[113,126],"represent":[115],"each":[116],"player's":[117],"suspicion":[118,140],"levels":[119],"toward":[120,169],"others.":[121],"By":[122],"combining":[123],"this":[124],"ToM":[125],"with":[127,153],"Monte":[128],"Carlo":[129],"Tree":[130],"Search":[131],"(MCTS),":[132],"our":[133],"agent":[134],"identifies":[135],"communication":[136],"strategies":[137],"minimize":[139],"directed":[141],"at":[142,184],"itself.":[143],"Through":[144],"comprehensive":[145],"evaluation":[146],"both":[148],"agent-versus-agent":[149],"simulations":[150],"studies":[152],"human":[154],"players,":[155],"demonstrate":[157],"MultiMind's":[158],"superior":[159],"performance":[160],"gameplay.":[162],"Our":[163,180],"work":[164],"presents":[165],"significant":[167],"advancement":[168],"LLM":[170],"capable":[172],"human-like":[174],"across":[177],"domains.":[179],"code":[181],"is":[182],"available":[183],"https://github.com/CjangCjengh/onuw.":[185]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
