[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-long-context-evaluation":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"d2272356-7c42-4c25-b455-03cf41d00eb8","long-context evaluation","long-context-evaluation",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"cec2d028-df49-4444-a0e2-e857109414bf","longmemeval-v2-agent-memory-web-workflows-zh","LongMemEval-V2：測 agent 長期記憶","LongMemEval-V2 用 451 題測試 agent 能否記住 Web 環境經驗，而不只是使用者歷史；結果顯示以 coding agent 蒐證的記憶法準確率最高，但延遲也更高。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778653249376-2wo2.png","zh","2026-05-13T06:20:29.320872+00:00"]