[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-ai-agent-tries-to-referee-conflicting-mecfs-medical-guidelines":10,"sections":40},{"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":35,"feedback":39,"feedback_at":22,"cost_usd":39,"total_tokens":39},8471,"ai-agent-tries-to-referee-conflicting-mecfs-medical-guidelines","AI Agent Tries to Referee Conflicting ME\u002FCFS Medical Guidelines","An unreviewed arXiv preprint says its ARCagent system hit 95.3% accuracy answering ME\u002FCFS questions by explicitly modeling where medical guidelines disagree.","A new AI agent claims it can answer questions about ME\u002FCFS correctly even when the official medical guidelines contradict each other.\n\nThe system, called ARCagent, is described in an arXiv preprint (arXiv:2609.36392) posted this week and has not been peer-reviewed. Its authors built a 1,706-chunk knowledge base pulled from 10 sources, tagged with a conflict registry that maps where competing ME\u002FCFS diagnostic frameworks disagree on treatment. A retrieval pipeline then re-ranks evidence using those conflict signals instead of treating every source as equally reliable. The authors also built their own benchmark, scored by a separate LLM acting as judge rather than keyword matching, and report that ARCagent hit 95.3% accuracy, ahead of baseline LLMs, while arguing keyword-based scoring undercounts correct answers by 10.1 percentage points on average.\n\nME\u002FCFS is a useful stress test for retrieval-augmented AI precisely because there is no single settled truth to retrieve. Diagnostic frameworks for the disease coexist and disagree, so an AI that just fetches the most relevant passage can confidently repeat one camp's position while ignoring the dispute entirely. The more interesting output here may be the conflict registry itself, a structured map of where medical authorities disagree, rather than the accuracy score attached to it.\n\nAll of this comes from one un-peer-reviewed preprint, with a benchmark the same team designed and an LLM judging the answers. The code is on GitHub, so the 95.3% figure is at least checkable, but treat it as a research claim, not a verdict.","[\"ai\",\"clinical-ai\",\"me-cfs\",\"research\"]","2026-09-30T04:00:00.000Z","2026-09-30T05:46:55.387Z","2026-09-30T05:47:01.512Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Attribute every claim and figure to its actual source — name this as an arXiv preprint (arXiv:2609.36392, posted this week) rather than presenting 1,706-chunk\u002F95.3%\u002F10.1-point figures as free-floating facts, and note it has not been peer-reviewed, so readers can verify the claims.","resolved","ai",[30,32,33,34],"clinical-ai","me-cfs","research",[36],{"name":37,"url":38},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.36392",0,{"sections":41},[42,45,49,53,58,63,68,73,78,83,88,93,98,103],{"name":43,"slug":30,"count":44,"latest_published_at":18},"AI",5029,{"name":46,"slug":47,"count":48,"latest_published_at":18},"Security","security",780,{"name":50,"slug":51,"count":52,"latest_published_at":18},"Policy","policy",417,{"name":54,"slug":55,"count":56,"latest_published_at":57},"Deals","deals",284,"2026-09-29T21:00:00.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":62},"Hardware","hardware",194,"2026-09-29T13:16:04.000Z",{"name":64,"slug":65,"count":66,"latest_published_at":67},"Science","science",154,"2026-09-28T13:19:18.000Z",{"name":69,"slug":70,"count":71,"latest_published_at":72},"Consumer Tech","consumer-tech",142,"2026-09-29T18:38:03.000Z",{"name":74,"slug":75,"count":76,"latest_published_at":77},"Software","software",91,"2026-09-25T20:55:00.000Z",{"name":79,"slug":80,"count":81,"latest_published_at":82},"Dev Tools","dev-tools",89,"2026-09-29T17:15:00.000Z",{"name":84,"slug":85,"count":86,"latest_published_at":87},"Startups","startups",83,"2026-09-29T21:51:36.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"General","general",49,"2026-09-28T16:44:57.000Z",{"name":94,"slug":95,"count":96,"latest_published_at":97},"Gaming","gaming",48,"2026-09-25T18:35:21.000Z",{"name":99,"slug":100,"count":101,"latest_published_at":102},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":104,"slug":105,"count":106,"latest_published_at":107},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]