[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-framework-lets-ai-models-decide-their-own-reasoning-steps":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},9002,"new-framework-lets-ai-models-decide-their-own-reasoning-steps","New Framework Lets AI Models Decide Their Own Reasoning Steps","Researchers built Hermes, a training method that teaches smaller open-source models to manage their own inference compute instead of following rigid rules.","A new paper argues that AI models should decide for themselves how to use extra \"thinking time,\" rather than following a fixed script written by their software harness.\n\nResearchers introduce a family of harnesses called Hermes that let a model control how it allocates and reuses context windows during inference, plus a training method called Hermes-Learn that teaches models this skill directly instead of hard-coding the rules into the surrounding system. In tests, models that already reasoned well could exploit that flexibility to get more out of extra inference-time compute. Smaller open-source models could not do this on their own. After training with Hermes-Learn, those smaller models learned to adapt their strategy based on both the specific problem and how far their reasoning had already progressed.\n\nTest-time scaling - giving a model more compute per query instead of training a bigger one - is one of the cheaper levers labs have for squeezing out better performance without a full retrain. This work suggests the limiting factor isn't just how much extra compute you hand a model, but whether it knows what to do with it, a skill that currently splits along lines of model size and training approach. The reported gains held across different benchmarks and models, and reportedly carried over to other test-time scaling methods beyond Hermes itself.\n\nPromising, but it's one paper without named benchmarks or released code in hand, so \"closes the gap\" is a claim worth watching, not a verdict.","[\"ai\",\"test-time-scaling\",\"llm-reasoning\",\"open-source-ai\"]","2026-10-01T04:00:00.000Z","2026-10-01T15:11:56.268Z","2026-10-01T15:12:00.726Z","published",null,[],"ai",[24,26,27,28],"test-time-scaling","llm-reasoning","open-source-ai",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.38332",0,{"sections":35},[36,39,43,48,53,58,62,67,72,76,81,86,91,96],{"name":37,"slug":24,"count":38,"latest_published_at":18},"AI",5487,{"name":40,"slug":41,"count":42,"latest_published_at":18},"Security","security",809,{"name":44,"slug":45,"count":46,"latest_published_at":47},"Policy","policy",429,"2026-10-01T02:26:17.000Z",{"name":49,"slug":50,"count":51,"latest_published_at":52},"Deals","deals",298,"2026-09-30T21:00:26.000Z",{"name":54,"slug":55,"count":56,"latest_published_at":57},"Hardware","hardware",196,"2026-09-30T13:00:00.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":18},"Science","science",162,{"name":63,"slug":64,"count":65,"latest_published_at":66},"Consumer Tech","consumer-tech",149,"2026-09-30T22:57:11.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":71},"Dev Tools","dev-tools",93,"2026-10-01T02:30:48.000Z",{"name":73,"slug":74,"count":70,"latest_published_at":75},"Software","software","2026-09-30T21:41:11.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Startups","startups",84,"2026-09-30T20:39:09.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Gaming","gaming",51,"2026-09-30T16:24:30.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"General","general",50,"2026-09-30T21:37:54.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]