[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-llms-now-help-refine-not-replace-cognitive-science-models":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},9875,"llms-now-help-refine-not-replace-cognitive-science-models","LLMs Now Help Refine, Not Replace, Cognitive Science Models","A new AI pipeline edits human-built cognitive models instead of replacing them, and finds a small set of code fixes explains most of the improvement.","A new hybrid system uses AI agents to fix human-built models of how people reason, instead of starting from scratch.\n\nResearchers built a pipeline that takes existing probabilistic programs, hand-coded models of human cognitive algorithms, and hands them to a system of LLM agents. The agents find mismatches between a model's predictions and real human behavior, propose specific code-level edits within constraints set by the researchers, and check that those edits do not break the model's structure. A probabilistic inference module then recomputes how well the revised model explains the behavioral data. The team tested this on a problem-solving task designed to surface different reasoning strategies, and the revised models consistently fit human behavior better than the originals.\n\nThis sits between two approaches that each have obvious flaws: hand-built cognitive models are interpretable but slow to improve, while pure LLM-generated models are scalable but opaque and mostly untested on anything as complex as recovering an algorithm from behavior. By having AI agents make targeted edits instead of writing a model from a blank slate, researchers keep the parts of their theory they trust while letting a machine surface fixes they missed. The paper also reports that a small, recurring set of code tweaks accounted for most of the improvement, hinting that human reasoning strategies on this task cluster into a manageable number of variants rather than infinite idiosyncrasy.\n\nIt is a narrow, technical result, but it points to a more useful role for LLMs in science: patching existing theories instead of replacing them outright.","[\"ai\",\"cognitive-science\",\"llm-agents\",\"research\"]","2026-10-05T04:00:00.000Z","2026-10-05T11:30:35.764Z","2026-10-05T11:30:47.352Z","published",null,[],"ai",[24,26,27,28],"cognitive-science","llm-agents","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.02523",0,{"sections":35},[36,39,43,48,53,58,62,67,71,75,80,85,90,95],{"name":37,"slug":24,"count":38,"latest_published_at":18},"AI",6164,{"name":40,"slug":41,"count":42,"latest_published_at":18},"Security","security",859,{"name":44,"slug":45,"count":46,"latest_published_at":47},"Policy","policy",444,"2026-10-03T15:02:01.000Z",{"name":49,"slug":50,"count":51,"latest_published_at":52},"Deals","deals",323,"2026-10-04T13:00:00.000Z",{"name":54,"slug":55,"count":56,"latest_published_at":57},"Hardware","hardware",204,"2026-10-03T14:50:50.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":18},"Science","science",177,{"name":63,"slug":64,"count":65,"latest_published_at":66},"Consumer Tech","consumer-tech",158,"2026-10-03T03:21:12.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":18},"Dev Tools","dev-tools",97,{"name":72,"slug":73,"count":70,"latest_published_at":74},"Software","software","2026-10-04T10:00:00.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Startups","startups",92,"2026-10-04T14:36:25.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",53,"2026-10-02T02:50:39.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"General","general",51,"2026-10-05T02:35:01.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"Reviews","reviews",32,"2026-10-02T18:00:00.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"How-To","how-to",7,"2026-10-01T09:00:00.000Z"]