[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-robot-skills-learned-with-just-10-minutes-of-real-testing":10,"sections":45},{"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":34,"tags":35,"sources":40,"feedback":44,"feedback_at":22,"cost_usd":44,"total_tokens":44},9096,"robot-skills-learned-with-just-10-minutes-of-real-testing","Robot Skills Learned With Just 10 Minutes of Real Testing","SimEX trains coding agents to control real robots using simulation first, needing only 10 minutes of real-robot interaction to master tasks like towel folding.","A new framework called SimEX teaches robots real-world skills almost entirely through simulation, then needs only 10 minutes of real-robot interaction to finish the job.\n\nSimEX pairs a coding agent with a physics simulator in two stages. First, the agent runs open-ended trial and error entirely in simulation, building a toolbox of robot skills without any human demonstrations. Then it tries that toolbox on a real robot: each physical trial is used to correct the simulator itself, and the corrected simulator helps diagnose what went wrong and test fixes. Researchers validated the approach on manipulation tasks including towel folding, barcode scanning, and plate handling, with only 10 minutes of real-robot interaction required.\n\nMost robot-learning methods either hand-code rules that break down in messy real environments, or rely on slow, costly, occasionally risky trial-and-error on physical hardware. SimEX instead treats the simulator as a workable lab assistant for a coding agent's own reasoning, not just a dataset generator, which is why the real-world portion of training shrinks to minutes rather than hours. That reframes simulation's job: less about perfectly mirroring reality, more about giving an AI agent a cheap place to think out loud.\n\nIt's three tasks in one lab, not a general-purpose robot brain - but if 10 minutes of real-robot interaction holds up on harder jobs, building robot skills starts looking more like debugging code than training an animal.","[\"robotics\",\"ai agents\",\"simulation\",\"sim-to-real\"]","2026-10-01T04:00:00.000Z","2026-10-01T19:46:43.176Z","2026-10-01T19:46:44.842Z","published",null,[24,30],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Verify whether the 10-minute real-robot practice figure is per task or a total across all three tasks before stating 'per task' in the headline, dek, and body—the source only says 'only 10 minutes of real-robot interaction' without specifying per-task, so the current wording invents a level of precision (and implies 3x the total hands-on time) that isn't supported.","resolved",{"id":31,"reviewer":26,"round":32,"reason":33,"status":29},"editor-r2",2,"The dek still invents precision by calling the 10 minutes a 'total,' and the body's parenthetical self-admission that the paper doesn't specify is an unattributed reporting-gap aside — instead, state the 10-minute figure exactly as the source phrases it everywhere (headline, dek, body) without characterizing it as per-task or total, and drop the self-admitted-gap aside.","ai",[36,37,38,39],"robotics","ai agents","simulation","sim-to-real",[41],{"name":42,"url":43},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.38982",0,{"sections":46},[47,51,55,59,64,69,73,78,83,88,93,98,103,108],{"name":48,"slug":34,"count":49,"latest_published_at":50},"AI",5839,"2026-10-02T04:00:00.000Z",{"name":52,"slug":53,"count":54,"latest_published_at":50},"Security","security",832,{"name":56,"slug":57,"count":58,"latest_published_at":50},"Policy","policy",438,{"name":60,"slug":61,"count":62,"latest_published_at":63},"Deals","deals",317,"2026-10-01T22:00:00.000Z",{"name":65,"slug":66,"count":67,"latest_published_at":68},"Hardware","hardware",198,"2026-10-01T17:38:48.000Z",{"name":70,"slug":71,"count":72,"latest_published_at":50},"Science","science",170,{"name":74,"slug":75,"count":76,"latest_published_at":77},"Consumer Tech","consumer-tech",155,"2026-10-01T19:54:10.000Z",{"name":79,"slug":80,"count":81,"latest_published_at":82},"Dev Tools","dev-tools",96,"2026-10-01T16:57:03.000Z",{"name":84,"slug":85,"count":86,"latest_published_at":87},"Software","software",93,"2026-09-30T21:41:11.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"Startups","startups",90,"2026-10-01T21:55:22.000Z",{"name":94,"slug":95,"count":96,"latest_published_at":97},"Gaming","gaming",53,"2026-10-02T02:50:39.000Z",{"name":99,"slug":100,"count":101,"latest_published_at":102},"General","general",50,"2026-09-30T21:37:54.000Z",{"name":104,"slug":105,"count":106,"latest_published_at":107},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":109,"slug":110,"count":111,"latest_published_at":112},"How-To","how-to",7,"2026-10-01T09:00:00.000Z"]