[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-reasoning-models-learn-to-stop-rambling-by-predicting-confidence":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},8327,"reasoning-models-learn-to-stop-rambling-by-predicting-confidence","Reasoning Models Learn to Stop Rambling by Predicting Confidence","Training AI models to judge their own confidence cuts reasoning length by up to 25 percent, no explicit efficiency training required.","A new self-supervised training method cuts AI reasoning length by up to 25% without ever telling the model to be shorter.\n\nResearchers fine-tuned reasoning models to predict their own confidence at points along their reasoning traces, using just 600 training problems. The training loss never mentions length, efficiency, or stopping - only confidence. At inference time, the models run standard generation with no early-stopping trick bolted on. Tested on Gemma, Qwen, Nemotron, and GPT-OSS models across math, science, and coding benchmarks, the fine-tuned versions matched baseline accuracy while generating up to 25% fewer tokens, on par with methods built explicitly to shorten reasoning.\n\nThat matters because inference cost is the real tax on reasoning models: every extra token a model rambles through costs money and time, and most fixes so far have meant either penalizing length during training or bolting on early-stopping logic at inference. This result suggests efficiency can show up as a side effect of teaching a model to track its own certainty, without engineers having to explicitly optimize for brevity at all.\n\nStill, this is one early paper trained on 600 problems, not a peer-reviewed, large-scale result - and getting a model to accurately judge its own confidence is a notoriously shaky foundation to build on.","[\"reasoning-models\",\"llm-efficiency\",\"ai-research\",\"machine-learning\"]","2026-09-28T04:00:00.000Z","2026-09-29T00:29:17.266Z","2026-09-29T00:29:24.379Z","published",null,[],"ai",[26,27,28,29],"reasoning-models","llm-efficiency","ai-research","machine-learning",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.31619",0,{"sections":36},[37,41,46,51,56,61,66,71,76,81,86,91,96,101],{"name":38,"slug":24,"count":39,"latest_published_at":40},"AI",4917,"2026-09-28T23:39:20.000Z",{"name":42,"slug":43,"count":44,"latest_published_at":45},"Security","security",768,"2026-09-29T01:20:00.000Z",{"name":47,"slug":48,"count":49,"latest_published_at":50},"Policy","policy",406,"2026-09-28T19:04:09.000Z",{"name":52,"slug":53,"count":54,"latest_published_at":55},"Deals","deals",272,"2026-09-28T17:42:46.000Z",{"name":57,"slug":58,"count":59,"latest_published_at":60},"Hardware","hardware",191,"2026-09-28T15:45:00.000Z",{"name":62,"slug":63,"count":64,"latest_published_at":65},"Science","science",154,"2026-09-28T13:19:18.000Z",{"name":67,"slug":68,"count":69,"latest_published_at":70},"Consumer Tech","consumer-tech",139,"2026-09-28T17:09:47.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Software","software",91,"2026-09-25T20:55:00.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Dev Tools","dev-tools",87,"2026-09-28T16:11:42.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Startups","startups",80,"2026-09-28T17:50:28.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"General","general",49,"2026-09-28T16:44:57.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Gaming","gaming",48,"2026-09-25T18:35:21.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":102,"slug":103,"count":104,"latest_published_at":105},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]