[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-researchers-publish-open-recipe-for-post-training-glm-45-air":10,"sections":40},{"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":30,"tags":31,"sources":35,"feedback":39,"feedback_at":22,"cost_usd":39,"total_tokens":39},7875,"researchers-publish-open-recipe-for-post-training-glm-45-air","Researchers Publish Open Recipe for Post-Training GLM-4.5-Air","A new arXiv paper lays out an eight-stage post-training pipeline that beats GLM-4.5-Air's official release without new human-labeled data.","A team of researchers has published a full, reproducible recipe for turning a big open base model into a sharper one, and they show all their work.\n\nThe paper, posted to arXiv on September 25, 2026 (arXiv:2609.29421, https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.29421), describes Rufus-Air, a post-training pipeline built on GLM-4.5-Air-Base, a 106-billion-parameter model that activates 12 billion parameters per token. The recipe runs eight stages in order: supervised fine-tuning, then reinforcement learning for reasoning, coding, and instruction-following, then agent training for general tasks, coding, and search, and finally reinforcement learning from human feedback. The authors say every stage relies on open-source components and public data, with no new human annotation and no proprietary model used to generate training examples. They report that the result beats GLM-4.5-Air's official post-trained release and holds its own against other open models of similar size.\n\nPost-training is usually the part labs keep closed even when the base model is open, because fine-tuning and reinforcement learning are where most real performance gains happen. Publishing the exact stage order, reward design, and data sources removes a lot of guesswork for anyone trying to replicate strong instruction-following and agentic behavior without a large annotation budget.\n\nIt is not a new model so much as a documented shortcut, useful if you already trust GLM-4.5-Air's base weights and less useful if you do not.","[\"ai\",\"open-source\",\"llm\",\"post-training\"]","2026-09-25T04:00:00.000Z","2026-09-26T04:05:24.767Z","2026-09-26T04:05:31.640Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Add basic sourcing for the paper — arXiv ID\u002Flink and publication date — since the entire story rests on a single unlinked, undated 'new paper' reference.","resolved","ai",[30,32,33,34],"open-source","llm","post-training",[36],{"name":37,"url":38},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.29421",0,{"sections":41},[42,46,51,56,61,66,71,76,81,86,91,96,101,106],{"name":43,"slug":30,"count":44,"latest_published_at":45},"AI",4589,"2026-09-25T21:57:05.000Z",{"name":47,"slug":48,"count":49,"latest_published_at":50},"Security","security",743,"2026-09-25T21:09:27.000Z",{"name":52,"slug":53,"count":54,"latest_published_at":55},"Policy","policy",392,"2026-09-25T18:44:30.000Z",{"name":57,"slug":58,"count":59,"latest_published_at":60},"Deals","deals",256,"2026-09-25T17:00:53.000Z",{"name":62,"slug":63,"count":64,"latest_published_at":65},"Hardware","hardware",185,"2026-09-25T15:00:22.000Z",{"name":67,"slug":68,"count":69,"latest_published_at":70},"Science","science",142,"2026-09-25T14:07:46.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Consumer Tech","consumer-tech",132,"2026-09-25T15:30:00.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Software","software",90,"2026-09-25T20:55:00.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Dev Tools","dev-tools",82,"2026-09-25T09:59:40.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"Startups","startups",76,"2026-09-25T18:33:59.000Z",{"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},"General","general",46,"2026-09-25T02:12:57.000Z",{"name":102,"slug":103,"count":104,"latest_published_at":105},"Reviews","reviews",30,"2026-09-24T20:07:31.000Z",{"name":107,"slug":108,"count":109,"latest_published_at":110},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]