[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-auto-mined-agent-skills-are-readable-but-dont-transfer":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},1687,"auto-mined-agent-skills-are-readable-but-dont-transfer","Auto-Mined Agent Skills Are Readable But Don't Transfer","A new study mines GUI interaction logs to build readable skill libraries for AI agents, but finds those skills don't transfer to new tasks.","A new pipeline can extract readable, named skills from AI agent interaction logs — but those skills don't actually make agents any better at new tasks.\n\nResearchers built a three-stage system that mines GUI trajectories — the click-by-click recordings of agents completing tasks — breaks them into segments, clusters those segments into candidate skills, and then trains a new agent policy on the resulting annotations. The mined clusters look coherent: five of eight clusters scored at least 0.95 purity against InteraSkill Workflows labels. The team then trained an agent using GRPO, a reinforcement learning method, on those skill annotations and tested against two benchmarks.\n\nThe results are candid about the limits. GRPO improved IW skill-step accuracy from 18.5% to 20.5% — a two-point gain that barely beats a simple frequency prior — and left BrowseComp+ scores essentially unchanged. The paper's core finding is that readable structure in mined data doesn't guarantee that structure is the right one for policy learning.\n\nThe researchers call this a diagnostic study rather than a system to deploy, which is either unusual modesty in an era of AI benchmark racing, or a sign that the gap between \"a human can read this skill library\" and \"an agent can learn from it\" is wider than the field has assumed.","[\"ai\",\"agents\",\"research\",\"machine-learning\"]","2026-06-19T04:00:00.000Z","2026-06-19T09:58:18.444Z","2026-06-19T14:21:37.064Z","published",null,[],"ai",[24,26,27,28],"agents","research","machine-learning",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.20363",0,{"sections":35},[36,39,43,48,53,58,63,67,71,76,81,86,91,96],{"name":37,"slug":24,"count":38,"latest_published_at":18},"AI",490,{"name":40,"slug":41,"count":42,"latest_published_at":18},"Security","security",132,{"name":44,"slug":45,"count":46,"latest_published_at":47},"Policy","policy",88,"2026-06-16T09:26:09.000Z",{"name":49,"slug":50,"count":51,"latest_published_at":52},"Consumer Tech","consumer-tech",78,"2026-06-16T17:58:24.000Z",{"name":54,"slug":55,"count":56,"latest_published_at":57},"Hardware","hardware",62,"2026-06-18T15:24:16.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":62},"Deals","deals",58,"2026-06-19T14:43:50.000Z",{"name":64,"slug":65,"count":61,"latest_published_at":66},"Software","software","2026-06-16T20:00:00.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":18},"Dev Tools","dev-tools",50,{"name":72,"slug":73,"count":74,"latest_published_at":75},"Science","science",38,"2026-06-18T04:00:00.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Gaming","gaming",31,"2026-06-16T15:25:13.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"General","general",26,"2026-06-13T18:35:15.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"Startups","startups",23,"2026-06-16T15:00:00.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Reviews","reviews",19,"2026-06-14T08:00:00.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]