[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-math-reasoning":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"41b062fe-1a6e-49ff-a27e-a3f511f431ee","math reasoning","math-reasoning",2,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"6911e614-4894-4f1f-a0ad-816e323793ef","retrieval-augmented-reinforcement-fine-tuning-analogy-zh","RA-RFT 讓模型學會類比推理","RA-RFT 把檢索目標從相似度改成「有助推理的類比」，再用這些示範做強化式微調，讓模型在數學推理上更會借題發揮。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781245983485-miul.png","zh","2026-06-12T06:32:27.726554+00:00"]