[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-multi-agent-rl":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"ae05905b-6972-4b66-a8f2-d94d4f58a7df","multi-agent RL","multi-agent-rl",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"9580adce-69ec-4880-ad8b-227c384cb377","marlin-greener-llm-inference-datacenters-zh","MARLIN 用多代理 RL 省雲端推理資源","MARLIN 把雲端 LLM 推理視為多代理協調問題，用遊戲理論式強化學習來追求更永續的資料中心運作。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779084247021-qzhd.png","zh","2026-05-18T06:03:35.259834+00:00"]