[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-study-maps-how-ai-agents-adopt-beliefs-from-peers":10,"sections":35},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},9889,"study-maps-how-ai-agents-adopt-beliefs-from-peers","Study Maps How AI Agents Adopt Beliefs From Peers","A new study finds LLM agents adopt beliefs via a sigmoid tipping point driven by claim plausibility, source trust, and the agent's own priors.","AI agents catch ideas from each other the same way humans do, complete with tipping points and stubborn groupthink.\n\nResearchers ran experiments where large language model agents were shown claims already endorsed by a varying number of peer agents, then measured the odds each agent adopted the claim. The resulting adoption curve was sigmoid, the signature of what epidemiologists call complex contagion: a claim needs a critical mass of peer support before it spreads, not just a single exposure. Where that tipping point sits depends on three things: how plausible the claim sounds, how reliable its source seems, and the individual agent's own leanings. The researchers found those three factors collapse into a single variable, essentially how well the new claim fits with what the agent already believes.\n\nZoom out to a population of interacting agents and the effects compound. Claims spread further on tightly clustered networks than on random ones, the system can flip suddenly once a cascade threshold is crossed, and once a belief takes hold it becomes far harder to dislodge than it was to establish. For anyone building multi-agent AI systems, or worried about them amplifying misinformation at scale, that asymmetry is the real finding: these systems are prone to getting stuck, not just to agreeing.\n\nIt is the same pattern public health researchers map in rumor spread and vaccine hesitancy, minus the part where populations eventually get bored, forget, and move on.","[\"ai agents\",\"llm\",\"social contagion\",\"multi-agent systems\"]","2026-10-05T04:00:00.000Z","2026-10-05T12:03:30.126Z","2026-10-05T12:03:36.705Z","published",null,[],"ai",[26,27,28,29],"ai agents","llm","social contagion","multi-agent systems",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.02654",0,{"sections":36},[37,40,44,49,54,59,63,68,72,76,81,86,91,96],{"name":38,"slug":24,"count":39,"latest_published_at":18},"AI",6168,{"name":41,"slug":42,"count":43,"latest_published_at":18},"Security","security",859,{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",444,"2026-10-03T15:02:01.000Z",{"name":50,"slug":51,"count":52,"latest_published_at":53},"Deals","deals",323,"2026-10-04T13:00:00.000Z",{"name":55,"slug":56,"count":57,"latest_published_at":58},"Hardware","hardware",204,"2026-10-03T14:50:50.000Z",{"name":60,"slug":61,"count":62,"latest_published_at":18},"Science","science",177,{"name":64,"slug":65,"count":66,"latest_published_at":67},"Consumer Tech","consumer-tech",158,"2026-10-03T03:21:12.000Z",{"name":69,"slug":70,"count":71,"latest_published_at":18},"Dev Tools","dev-tools",97,{"name":73,"slug":74,"count":71,"latest_published_at":75},"Software","software","2026-10-04T10:00:00.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Startups","startups",92,"2026-10-04T14:36:25.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Gaming","gaming",53,"2026-10-02T02:50:39.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"General","general",51,"2026-10-05T02:35:01.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Reviews","reviews",32,"2026-10-02T18:00:00.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"How-To","how-to",7,"2026-10-01T09:00:00.000Z"]