Large Language Models Simulating Deception and Coalition in Social Deduction Game

Large Language Models Simulating Deception and Coalition in Social Deduction Game | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Large Language Models Simulating Deception and Coalition in Social Deduction Game Atharva Thakur, Shruti Dhumal This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8456872/v2 This work is licensed under a CC BY 4.0 License Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Abstract This study examines deceptive behaviors, coalition formation, and hidden-role reasoning in Large Language Models (LLMs) playing the social deduction game Secret Hitler. Through a case-study analysis of a simulated five-player game log—with three Loyalist and two Spy agents—we dissect dialogues and actions to reveal emergent strategies in asymmetric information environments. Key findings highlight Spies' tactical deception, such as framing statements to build false trust and selectively misreporting policy draws, contrasted with Loyalists' emphasis on transparency to foster genuine alliances. Coalition dynamics arise from aligned reasoning and endorsements, enabling Spies to reinforce covert strategies, while a policy progression table illustrates how bluffs influence round-by-round outcomes and trust erosion. Although LLMs demonstrate strategic adaptation and theory-of-mind inference, they exhibit limitations in subtle, incentive-aligned deception, often relying on explicit prompting. This analysis advances AI game-playing and LLM deception modeling by integrating empirical dialogue insights with broader implications for multi-agent alignment and social simulation. Artificial Intelligence and Machine Learning Large Language Models Social Deduction Games Multi-Agent Systems Deception Coalition Formation Theory of Mind Secret Hitler Emergent Behavior AI Alignment Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8456872","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":570845070,"identity":"8a71f8db-f4a7-4e7c-af70-b4d358e892ef","order_by":0,"name":"Atharva Thakur","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABF0lEQVRIiWNgGAWjYFACHjiLjYHhAAMDP4iZUIBHBxtcCzNEi2QDSIsBKVoMDoA4eLTwz+89+LmyzY7BvIH/2IMfZw7nG59fnfjhgQGDPL/YAaxaJI7xJUuebUtmkDnAzG7Yc+Ow5bYbbzdLAB1mOHN2AnZrjvEYSDacYWaQADpMgufDYQOzG2c3gLQkGNzGrkX+GI/xz4Yz9WAtkn+AWoxnnN38A58Wg2M8ZpINFYfBWqR5bhw2MODv3YbXFsNjOWaWDRXHeSSYmc2kZc6kG0jc4N1mkWAggdMvcofPGN9sMKiWk2BvfCb55pi1AX//2c03f1TYyPNL4/A+FPAwMMOYEmCVEniVowH+A6SoHgWjYBSMghEAALiWWB8HQNE6AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0004-8716-3861","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Atharva","middleName":"","lastName":"Thakur","suffix":""},{"id":570931981,"identity":"257f4d70-0b19-4b10-9666-4b60b573de6f","order_by":1,"name":"Shruti Dhumal","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Shruti","middleName":"","lastName":"Dhumal","suffix":""}],"badges":[],"createdAt":"2025-12-26 17:17:06","currentVersionCode":2,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8456872/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-8456872/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101397748,"identity":"91861669-364e-47bb-b6b7-1f9fc3ce54d6","added_by":"auto","created_at":"2026-01-29 09:36:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":592847,"visible":true,"origin":"","legend":"","description":"","filename":"ResearchPaperLargeLanguageModelsSimulatingDeceptionandCoalitioninSocialDeductionGame.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8456872/v2_covered_50a1a6b4-a1e8-41fc-a67f-851220d78fa7.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"Large Language Models Simulating Deception and Coalition in Social Deduction Game","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Large Language Models, Social Deduction Games, Multi-Agent Systems, Deception, Coalition Formation, Theory of Mind, Secret Hitler, Emergent Behavior, AI Alignment","lastPublishedDoi":"10.21203/rs.3.rs-8456872/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8456872/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study examines deceptive behaviors, coalition formation, and hidden-role reasoning in Large Language Models (LLMs) playing the social deduction game Secret Hitler. Through a case-study analysis of a simulated five-player game log\u0026mdash;with three Loyalist and two Spy agents\u0026mdash;we dissect dialogues and actions to reveal emergent strategies in asymmetric information environments. Key findings highlight Spies' tactical deception, such as framing statements to build false trust and selectively misreporting policy draws, contrasted with Loyalists' emphasis on transparency to foster genuine alliances. Coalition dynamics arise from aligned reasoning and endorsements, enabling Spies to reinforce covert strategies, while a policy progression table illustrates how bluffs influence round-by-round outcomes and trust erosion. Although LLMs demonstrate strategic adaptation and theory-of-mind inference, they exhibit limitations in subtle, incentive-aligned deception, often relying on explicit prompting. This analysis advances AI game-playing and LLM deception modeling by integrating empirical dialogue insights with broader implications for multi-agent alignment and social simulation.\u003c/p\u003e","manuscriptTitle":"Large Language Models Simulating Deception and Coalition in Social Deduction Game","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2026-01-27 20:20:59","doi":"10.21203/rs.3.rs-8456872/v2","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}},{"code":1,"date":"2026-01-07 12:37:34","doi":"10.21203/rs.3.rs-8456872/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"90b96224-426a-4677-b70d-a23618f32d8c","owner":[],"postedDate":"January 27th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":60745940,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-01-07T12:37:34+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-27 20:20:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-8456872","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8456872","identity":"rs-8456872","version":["v2"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}