[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-researchers-fold-agent-scaffolding-into-model-weights":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},7438,"researchers-fold-agent-scaffolding-into-model-weights","Researchers Fold Agent Scaffolding Into Model Weights","Harness-Zero trains AI models to absorb a specialized tool harness's behavior, matching or beating its performance once the harness is removed.","A new training method lets AI agents keep the skills of an elaborate support system even after that system is switched off.\n\nResearchers describe Harness-Zero, a technique for what they call agent harness distillation. An agent harness is the external scaffolding (code, prompts, and tool wrappers) that mediates how a model reads its environment and takes actions, and specialized harnesses tend to boost performance only for the exact setup they were built for. Harness-Zero uses a highly tuned harness to guide a second \"harnessing agent,\" which corrects a student model's responses so they work inside a simpler, fixed target harness. Those corrected trajectories become fine-tuning data, baking the specialized behavior into the model's weights so the elaborate harness can be removed entirely at deployment.\n\nThe gains hold up. Across knowledge-work, tool-use, and science tasks, the base model's average task success rose from 23.3% to 44.3% once the specialized harness was stripped away, actually beating the 41.7% it managed with that harness still attached. The model also recovered 82.3% of the specific behavioral patterns the harness had induced. That result echoes an old idea from a new angle: distillation has long been used to compress a big model's knowledge into a small one, but here the thing being distilled is not a model's outputs, it is the behavior of an entire tool-calling pipeline.\n\nIt is one paper's benchmark numbers, not a shipped product, and \"internalizing behavior\" is a tidy way of describing what is really a distillation shortcut around building better base models in the first place.","[\"ai agents\",\"agent harness\",\"llm training\",\"arxiv\"]","2026-09-23T04:00:00.000Z","2026-09-23T13:26:45.316Z","2026-09-23T13:26:50.303Z","published",null,[],"ai",[26,27,28,29],"ai agents","agent harness","llm training","arxiv",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.24974",0,{"sections":36},[37,41,45,50,55,60,65,70,75,80,85,90,95,100],{"name":38,"slug":24,"count":39,"latest_published_at":40},"AI",4347,"2026-09-23T12:00:00.000Z",{"name":42,"slug":43,"count":44,"latest_published_at":18},"Security","security",713,{"name":46,"slug":47,"count":48,"latest_published_at":49},"Policy","policy",371,"2026-09-23T12:00:43.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Deals","deals",211,"2026-09-23T13:00:46.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",170,"2026-09-23T11:59:23.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Science","science",134,"2026-09-23T09:00:00.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Consumer Tech","consumer-tech",110,"2026-09-22T20:00:00.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Software","software",81,"2026-09-23T09:56:13.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Dev Tools","dev-tools",79,"2026-09-22T22:21:13.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Startups","startups",65,"2026-09-22T22:06:48.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"Gaming","gaming",45,"2026-09-22T15:35:06.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"General","general",43,"2026-09-21T23:48:56.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"Reviews","reviews",27,"2026-09-22T13:00:00.000Z",{"name":101,"slug":102,"count":103,"latest_published_at":104},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]