[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-researchers-build-ai-that-keeps-its-fake-patients-in-character":10,"sections":34},{"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":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},10610,"researchers-build-ai-that-keeps-its-fake-patients-in-character","Researchers build AI that keeps its fake patients in character","A new multi-agent system aims to stop AI roleplay clients from drifting out of character during counselor training simulations.","A new framework called MASC aims to keep AI-simulated therapy clients from breaking character mid-session.\n\nResearchers behind an arXiv paper introduce MASC, a Multi-Agent Self-Calibration framework with latent construct alignment for consistent client role-playing in psychological counseling training. It combines construct-guided generation, collaborative refinement, consistency verification, and memory-based revision in a closed calibration loop that catches and corrects inconsistencies as a dialogue unfolds. The team also built CRPC-Bench, a benchmark of 38 motivational-interviewing client profiles annotated with Big-Five personality traits, turn-level psychological states, communicative actions, and emotions. In testing, MASC beat existing role-playing methods on profile, personality, receptivity, and turn-level consistency, with a heterogeneous agent configuration performing best.\n\nCounselor training often relies on scripted actors or static chatbot personas that either agree with everything the trainee says or lose their personality over a long conversation, which makes for weak practice reps. A simulated client that holds a consistent psychological profile across many turns is a precondition for using AI in clinical training at scale, and the benchmark itself may prove more useful than the framework, since it is one of the first to measure turn-by-turn consistency rather than just surface plausibility.\n\nWorth noting: this is a research prototype tested against other AI methods, not against real training outcomes with actual counselors, so whether more consistent personas produce better-trained therapists is still an open question.","[\"ai\",\"mental-health\",\"research\",\"multi-agent\"]","2026-10-07T04:00:00.000Z","2026-10-08T22:41:58.634Z","2026-10-08T22:42:02.919Z","published",null,[],"ai",[24,26,27,28],"mental-health","research","multi-agent",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.08250",0,{"sections":35},[36,40,45,50,55,60,65,70,75,79,84,89,94,99],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",6448,"2026-10-07T18:45:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":44},"Security","security",904,"2026-10-07T19:53:42.000Z",{"name":46,"slug":47,"count":48,"latest_published_at":49},"Policy","policy",474,"2026-10-07T18:23:21.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Deals","deals",453,"2026-10-07T23:58:31.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",222,"2026-10-07T21:19:54.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Science","science",186,"2026-10-06T21:20:39.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Consumer Tech","consumer-tech",174,"2026-10-07T17:41:41.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Software","software",113,"2026-10-07T18:10:00.000Z",{"name":76,"slug":77,"count":73,"latest_published_at":78},"Startups","startups","2026-10-07T23:36:57.000Z",{"name":80,"slug":81,"count":82,"latest_published_at":83},"Dev Tools","dev-tools",105,"2026-10-07T16:59:11.000Z",{"name":85,"slug":86,"count":87,"latest_published_at":88},"General","general",61,"2026-10-07T22:00:24.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"Gaming","gaming",56,"2026-10-07T12:00:00.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Reviews","reviews",33,"2026-10-05T11:57:17.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"How-To","how-to",8,"2026-10-05T09:00:00.000Z"]