{"id":"https://openalex.org/W4387559637","doi":"https://doi.org/10.48550/arxiv.2310.05036","title":"AvalonBench: Evaluating LLMs Playing the Game of Avalon","display_name":"AvalonBench: Evaluating LLMs Playing the Game of Avalon","publication_year":2023,"publication_date":"2023-10-08","ids":{"openalex":"https://openalex.org/W4387559637","doi":"https://doi.org/10.48550/arxiv.2310.05036"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.05036","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.05036","pdf_url":"https://arxiv.org/pdf/2310.05036","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.05036","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Light, Jonathan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Light, Jonathan","raw_affiliation_strings":["Rensselaer Polytechnic Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute ,","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cai, Min","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cai, Min","raw_affiliation_strings":["Shenzhen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100784818","display_name":"Sheng Shen","orcid":"https://orcid.org/0000-0003-4734-1008","observed_orcids":["https://orcid.org/0000-0003-4734-1008"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shen, Sheng","raw_affiliation_strings":["University of California , Berkeley ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley ,","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060639952","display_name":"Ziniu Hu","orcid":"https://orcid.org/0009-0007-8818-739X","observed_orcids":["https://orcid.org/0009-0007-8818-739X"]},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hu, Ziniu","raw_affiliation_strings":["California Institute of Technology https ://github.com/ jonathanmli / Avalon -","LLM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology https ://github.com/ jonathanmli / Avalon -","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"LLM","institution_ids":[]}]}],"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":true,"cited_by_count":85,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9609000086784363,"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":0.9609000086784363,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.014499999582767487,"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/T10028","display_name":"Topic Modeling","score":0.005100000184029341,"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/avalon","display_name":"Avalon","score":0.7020000219345093},{"id":"https://openalex.org/keywords/resistance","display_name":"resistance","score":0.5559999942779541},{"id":"https://openalex.org/keywords/social-deduction-games","display_name":"social deduction games","score":0.9399999976158142},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.8360000252723694},{"id":"https://openalex.org/keywords/multi-agent-evaluation","display_name":"multi-agent evaluation","score":0.6869999766349792},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.6959999799728394},{"id":"https://openalex.org/keywords/react-agents","display_name":"ReAct agents","score":0.7089999914169312},{"id":"https://openalex.org/keywords/deception","display_name":"deception","score":0.5220000147819519},{"id":"https://openalex.org/keywords/negotiation","display_name":"negotiation","score":0.7770000100135803},{"id":"https://openalex.org/keywords/game-agents","display_name":"game-playing agents","score":0.4560000002384186},{"id":"https://openalex.org/keywords/self-play","display_name":"self-play","score":0.515999972820282}],"concepts":[{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.7547711133956909},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.612128734588623},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5463850498199463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5453065037727356},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44188234210014343},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.42955881357192993},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.4210916757583618},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.23823314905166626},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.22033163905143738},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.20078715682029724},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.08697628974914551},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.05036","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.05036","pdf_url":"https://arxiv.org/pdf/2310.05036","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.05036","doi":"https://doi.org/10.48550/arxiv.2310.05036","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.05036","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.05036","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.05036","pdf_url":"https://arxiv.org/pdf/2310.05036","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387559637.pdf","grobid_xml":"https://content.openalex.org/works/W4387559637.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2113609601","https://openalex.org/W4224912544","https://openalex.org/W4226227340","https://openalex.org/W4247737884","https://openalex.org/W4304195432","https://openalex.org/W4319165821","https://openalex.org/W4322718191","https://openalex.org/W4323572061","https://openalex.org/W4327810158","https://openalex.org/W4361229539","https://openalex.org/W4366330503","https://openalex.org/W4367628410","https://openalex.org/W4385682136","https://openalex.org/W7133224126","https://openalex.org/W7133231369","https://openalex.org/W7133244301"],"related_works":["https://openalex.org/W4404783650","https://openalex.org/W4402855388","https://openalex.org/W4412008426","https://openalex.org/W7162786612","https://openalex.org/W4392971563","https://openalex.org/W6979315260","https://openalex.org/W6921366255","https://openalex.org/W4399597482","https://openalex.org/W4414457883","https://openalex.org/W4416036101"],"abstract_inverted_index":{"In":[0],"this":[1,76],"paper,":[2],"we":[3,78],"explore":[4],"the":[5,15,64,155,180],"potential":[6],"of":[7,69,140,183],"Large":[8],"Language":[9],"Models":[10],"(LLMs)":[11],"Agents":[12],"in":[13,23,43,75,154],"playing":[14,134,145],"strategic":[16],"social":[17],"deduction":[18],"game,":[19],"Resistance":[20],"Avalon.":[21],"Players":[22],"Avalon":[24,58],"are":[25],"challenged":[26],"not":[27],"only":[28],"to":[29,41,62],"make":[30,57],"informed":[31],"decisions":[32],"based":[33,121],"on":[34,122],"dynamically":[35],"evolving":[36],"game":[37,84,97,185],"phases,":[38],"but":[39],"also":[40],"engage":[42],"discussions":[44],"where":[45],"they":[46],"must":[47],"deceive,":[48],"deduce,":[49],"and":[50,66,107,173],"negotiate":[51],"with":[52,112],"other":[53],"players.":[54],"These":[55],"characteristics":[56],"a":[59,82,96,125,137,163],"compelling":[60],"test-bed":[61,165],"study":[63],"decision-making":[65],"language-processing":[67],"capabilities":[68],"LLM":[70,90,110],"Agents.":[71,91],"To":[72],"facilitate":[73],"research":[74],"line,":[77],"introduce":[79],"AvalonBench":[80,123,160],"-":[81],"comprehensive":[83],"environment":[85,98],"tailored":[86,113],"for":[87,99,115,166],"evaluating":[88],"multi-agent":[89],"This":[92],"benchmark":[93],"incorporates:":[94],"(1)":[95],"Avalon,":[100],"(2)":[101],"rule-based":[102,143],"bots":[103,144],"as":[104],"baseline":[105],"opponents,":[106],"(3)":[108],"ReAct-style":[109],"agents":[111],"prompts":[114],"each":[116],"role.":[117],"Notably,":[118],"our":[119],"evaluations":[120],"highlight":[124],"clear":[126],"capability":[127],"gap.":[128],"For":[129],"instance,":[130],"models":[131],"like":[132],"ChatGPT":[133],"good-role":[135,148],"got":[136],"win":[138,152],"rate":[139,153],"22.2%":[141],"against":[142],"evil,":[146],"while":[147],"bot":[149],"achieves":[150],"38.2%":[151],"same":[156],"setting.":[157],"We":[158],"envision":[159],"could":[161],"be":[162],"good":[164],"developing":[167],"more":[168],"advanced":[169],"LLMs":[170],"(with":[171],"self-playing)":[172],"agent":[174],"frameworks":[175],"that":[176],"can":[177],"effectively":[178],"model":[179],"layered":[181],"complexities":[182],"such":[184],"environments.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":51},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":8}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-10-12T00:00:00"}