[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-when-ai-agents-talk-wrong-answers-can-overrule-right-ones":10,"sections":41},{"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":30,"tags":31,"sources":36,"feedback":40,"feedback_at":22,"cost_usd":40,"total_tokens":40},8492,"when-ai-agents-talk-wrong-answers-can-overrule-right-ones","When AI Agents Talk, Wrong Answers Can Overrule Right Ones","A new study finds bad upstream AI messages flip correct answers in up to 32% of cases, and 94% of those flips are exact copies of the wrong answer.","Feed a large language model a wrong answer from another AI, and it will often believe it over its own correct reasoning.\n\nA paper posted to arXiv on September 30, 2026 (arXiv:2609.36855) ran controlled experiments on multi-agent LLM systems, in which one agent sends a message to a second agent working the same task. The researchers held the downstream agent's task and evidence fixed, then compared its answers under three conditions: no message, the upstream agent's real message, or a message deliberately flipped to the opposite conclusion. When the downstream agent would have answered correctly on its own, an incorrect upstream message still changed its answer in up to 32% of cases. Of those wrong flips, 94% were not scattered errors: the downstream agent simply copied the upstream agent's specific wrong answer, a pattern the researchers call answer substitution.\n\nThat matters because most multi-agent AI products assume more communication between agents is better. This study shows the opposite can also be true: a single bad message does not just fail to help, it can overwrite work the system already got right. The researchers found that filtering out unreliable messages recovers part of that lost accuracy, which suggests the fix is not more agents or more chatter, but agents that know when to disregard each other.\n\nIn other words, the multi-agent hype has a blind spot: teamwork only works if the team knows who not to listen to.","[\"multi-agent ai\",\"llm reliability\",\"ai research\",\"answer substitution\"]","2026-09-30T04:00:00.000Z","2026-09-30T07:03:44.345Z","2026-09-30T07:03:50.579Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Fix the dek, which conflates two different figures (it implies wrong answers get copied 94% of the time whenever the downstream agent was right, but the paper actually shows flips happen in up to 32% of those cases and only 94% of those flips are exact copies), and add explicit source attribution in the body (arXiv paper number and date) since the study is currently referenced only vaguely as 'researchers'.","resolved","ai",[32,33,34,35],"multi-agent ai","llm reliability","ai research","answer substitution",[37],{"name":38,"url":39},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.36855",0,{"sections":42},[43,46,50,54,59,64,69,74,79,84,89,94,99,104],{"name":44,"slug":30,"count":45,"latest_published_at":18},"AI",5028,{"name":47,"slug":48,"count":49,"latest_published_at":18},"Security","security",780,{"name":51,"slug":52,"count":53,"latest_published_at":18},"Policy","policy",417,{"name":55,"slug":56,"count":57,"latest_published_at":58},"Deals","deals",284,"2026-09-29T21:00:00.000Z",{"name":60,"slug":61,"count":62,"latest_published_at":63},"Hardware","hardware",194,"2026-09-29T13:16:04.000Z",{"name":65,"slug":66,"count":67,"latest_published_at":68},"Science","science",154,"2026-09-28T13:19:18.000Z",{"name":70,"slug":71,"count":72,"latest_published_at":73},"Consumer Tech","consumer-tech",142,"2026-09-29T18:38:03.000Z",{"name":75,"slug":76,"count":77,"latest_published_at":78},"Software","software",91,"2026-09-25T20:55:00.000Z",{"name":80,"slug":81,"count":82,"latest_published_at":83},"Dev Tools","dev-tools",89,"2026-09-29T17:15:00.000Z",{"name":85,"slug":86,"count":87,"latest_published_at":88},"Startups","startups",83,"2026-09-29T21:51:36.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",49,"2026-09-28T16:44:57.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Gaming","gaming",48,"2026-09-25T18:35:21.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":105,"slug":106,"count":107,"latest_published_at":108},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]