[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-synthetic-desktop-data-makes-computer-use-agents-click-better":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},9973,"synthetic-desktop-data-makes-computer-use-agents-click-better","Synthetic Desktop Data Makes Computer-Use Agents Click Better","A new synthetic desktop training environment called DeskForge sharply improved an AI agent's click accuracy and its ability to finish real multi-step tasks.","A research team has built a synthetic desktop factory to train AI agents on exactly where to click.\n\nThe project, called DeskForge, runs real applications inside a controllable environment that varies window layout, screen resolution, and app content to generate dense, labeled snapshots of what is on screen. Each snapshot fuses a screenshot, the accessibility tree, and window geometry, then records the outcome of every action taken. That pipeline produced DeskForge-1M, a dataset of 1.2 million annotated desktop observations covering 159.7 million individual on-screen elements. The team fine-tuned four vision-language models on 200,000 examples from that data; one of them, Qwen3.5-4B, gained 11.51 percentage points on the ScreenSpot-Pro benchmark and 10.11 points on OSWorld-G.\n\nThe more interesting number is what happens to actual task completion. Using the exact same planner, the fine-tuned Qwen3.5-4B solved 50 of 119 WebArena-Infinity tasks, up from 31, and 15 of 100 OpenApps tasks, up from 3. Nothing about the agent's reasoning changed, only its eyes - a sign that grounding, not planning, has been the quieter bottleneck for computer-use agents that still fumble basic clicks outside curated demos.\n\nStill, 15 out of 100 is a pass rate no product could ship on. Better synthetic training data narrows the gap; it does not close it.","[\"ai-agents\",\"computer-use-agents\",\"training-data\",\"benchmarks\"]","2026-10-05T04:00:00.000Z","2026-10-05T16:10:34.751Z","2026-10-05T16:10:38.576Z","published",null,[],"ai",[26,27,28,29],"ai-agents","computer-use-agents","training-data","benchmarks",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.02320",0,{"sections":36},[37,40,44,49,54,59,63,68,72,76,81,86,91,96],{"name":38,"slug":24,"count":39,"latest_published_at":18},"AI",6233,{"name":41,"slug":42,"count":43,"latest_published_at":18},"Security","security",868,{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",444,"2026-10-03T15:02:01.000Z",{"name":50,"slug":51,"count":52,"latest_published_at":53},"Deals","deals",323,"2026-10-04T13:00:00.000Z",{"name":55,"slug":56,"count":57,"latest_published_at":58},"Hardware","hardware",204,"2026-10-03T14:50:50.000Z",{"name":60,"slug":61,"count":62,"latest_published_at":18},"Science","science",177,{"name":64,"slug":65,"count":66,"latest_published_at":67},"Consumer Tech","consumer-tech",158,"2026-10-03T03:21:12.000Z",{"name":69,"slug":70,"count":71,"latest_published_at":18},"Dev Tools","dev-tools",97,{"name":73,"slug":74,"count":71,"latest_published_at":75},"Software","software","2026-10-04T10:00:00.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Startups","startups",92,"2026-10-04T14:36:25.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Gaming","gaming",53,"2026-10-02T02:50:39.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"General","general",51,"2026-10-05T02:35:01.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Reviews","reviews",32,"2026-10-02T18:00:00.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"How-To","how-to",7,"2026-10-01T09:00:00.000Z"]