[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-researchers-teach-gui-bots-to-rewrite-their-own-playbooks":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},6564,"researchers-teach-gui-bots-to-rewrite-their-own-playbooks","Researchers Teach GUI Bots to Rewrite Their Own Playbooks","EvoSkill-GUI lets AI agents that click through apps rewrite their own playbooks mid-task when pop-ups or moved buttons break the plan, without retraining.","GUI agents that click through apps and desktops can now patch their own playbooks on the fly, without retraining.\n\nResearchers built EvoSkill-GUI, a training-free framework that treats agent \"skills\" as living documents instead of fixed scripts written once and left alone. Each skill ships as a multi-file package: executable plans, backup ways to locate on-screen elements, failure-recovery rules, accessibility utilities, and a record of past failures. The system runs on a reflect-revise-reuse loop - the agent revises its plan instantly when something breaks mid-task, then a separate critic reviews failed attempts in isolation and edits specific skill files through a restricted interface, rather than letting the agent rewrite anything it wants. The team tested it on three benchmarks spanning mobile and desktop: MobileWorld, AndroidWorld, and OSWorld.\n\nThis matters because GUI agents fail for mundane reasons: a pop-up appears, a button moves, a page loads slowly, and a plan drawn up before the run falls apart. EvoSkill-GUI improved multiple base models with no extra training, gaining up to 16.2% on MobileWorld, 6.0% on AndroidWorld, and 10.5% on OSWorld, and the evolved skill libraries kept helping on related tasks instead of needing to be rebuilt from scratch each time.\n\nThose gains come from controlled benchmark environments, not the chaos of a real app pushing a surprise redesign overnight - the harder test is whether a self-patched skill file survives interfaces nobody built the benchmark to anticipate.","[\"ai-agents\",\"automation\",\"gui-automation\",\"research\"]","2026-09-17T04:00:00.000Z","2026-09-18T00:21:52.454Z","2026-09-18T00:22:04.383Z","published",null,[],"ai",[26,27,28,29],"ai-agents","automation","gui-automation","research",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.17653",0,{"sections":36},[37,41,45,50,55,59,63,68,73,77,82,87,92,97],{"name":38,"slug":24,"count":39,"latest_published_at":40},"AI",3853,"2026-09-17T08:27:09.000Z",{"name":42,"slug":43,"count":44,"latest_published_at":18},"Security","security",648,{"name":46,"slug":47,"count":48,"latest_published_at":49},"Policy","policy",338,"2026-09-11T04:00:00.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":18},"Hardware","hardware",154,{"name":60,"slug":61,"count":62,"latest_published_at":18},"Science","science",114,{"name":64,"slug":65,"count":66,"latest_published_at":67},"Consumer Tech","consumer-tech",99,"2026-09-09T17:27:33.000Z",{"name":69,"slug":70,"count":71,"latest_published_at":72},"Software","software",75,"2026-09-10T20:41:21.000Z",{"name":74,"slug":75,"count":76,"latest_published_at":18},"Dev Tools","dev-tools",73,{"name":78,"slug":79,"count":80,"latest_published_at":81},"Startups","startups",55,"2026-09-09T23:14:29.000Z",{"name":83,"slug":84,"count":85,"latest_published_at":86},"Gaming","gaming",43,"2026-09-10T12:18:06.000Z",{"name":88,"slug":89,"count":90,"latest_published_at":91},"General","general",41,"2026-09-08T01:57:23.000Z",{"name":93,"slug":94,"count":95,"latest_published_at":96},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":98,"slug":99,"count":100,"latest_published_at":101},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]