[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-agent-infra-rewrites-ai-infrastructure-zh":3,"tags-agent-infra-rewrites-ai-infrastructure-zh":33,"related-lang-agent-infra-rewrites-ai-infrastructure-zh":48,"related-posts-agent-infra-rewrites-ai-infrastructure-zh":52,"series-industry-87497399-e0aa-47bd-b17d-961dd8c683bb":89},{"id":4,"title":5,"content":6,"summary":7,"source":8,"source_url":9,"author":10,"image_url":11,"keywords":12,"language":21,"translated_content":10,"views":22,"is_premium":23,"created_at":24,"updated_at":24,"cover_image":11,"published_at":25,"rewrite_status":26,"rewrite_error":10,"rewritten_from_id":27,"slug":28,"category":29,"related_article_id":30,"status":31,"google_indexed_at":32,"x_posted_at":10,"tweet_text":10,"title_rewritten_at":10,"title_original":10,"key_takeaways":10,"topic_cluster_id":10,"embedding":10,"is_canonical_seed":23},"87497399-e0aa-47bd-b17d-961dd8c683bb","Agent 基礎設施正在重寫 AI","\u003Cp>2024 年，\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSWE-agent\u002FSWE-agent\" target=\"_blank\" rel=\"noopener\">SWE-agent\u003C\u002Fa> 直接把話講白了。Agent 表現，不只看模型本身。工具怎麼接、狀態怎麼存、任務怎麼排，結果差很多。\u003C\u002Fp>\u003Cp>接著，\u003Ca href=\"https:\u002F\u002Fwww.anthropic.com\" target=\"_blank\" rel=\"noopener\">Anthropic\u003C\u002Fa> 又把這件事往前推。它用 \u003Ca href=\"https:\u002F\u002Fmodelcontextprotocol.io\" target=\"_blank\" rel=\"noopener\">Model Context Protocol（MCP）\u003C\u002Fa>，把工具連接變成公開標準。這下子，AI 基礎設施的重心真的開始變了。\u003C\u002Fp>\u003Cp>講白了，以前大家在拼 Tok\u003Ca href=\"\u002Fnews\u002Fopenclaw-security-risks-and-defenses-zh\">en\u003C\u002Fa> 成本。現在更像在拼 Agent 能不能穩穩做事。能不能呼叫工具。能不能記住前一步。能不能在多個系統間協作。\u003C\u002Fp>\u003Ch2>2024 為什麼改變了 Agent 討論\u003C\u002Fh2>\u003Cp>以前的框架很簡單。模型越大，效果越好。參數越多，分數越高。很多人就以為，AI 工程的核心只剩推論服務。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775057778098-qqk6.png\" alt=\"Agent 基礎設施正在重寫 AI\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>但 Agent 出現後，這套說法開始漏氣。只要模型能規劃、能呼叫 API、能讀檔、能重試，周邊基礎設施就立刻變重要。說真的，模型只是大腦。環境才是整個身體。\u003C\u002Fp>\u003Cp>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSWE-agent\u002FSWE-agent\" target=\"_blank\" rel=\"noopener\">SWE-agent\u003C\u002Fa> 是很好的例子。它把軟體工程任務拿來測，結果很清楚：Agent-computer interface 會直接影響成功率。提示詞格式、工具輸出格式、回饋迴圈，這些都不是小事。\u003C\u002Fp>\u003Cp>Anthropic 的 Agent 指南也在講同一件事。生產環境裡，簡單、可組合的模式通常更穩。這句話很刺耳，但很真。很多團隊還在幻想大框架能解決一切，結果只是把失敗包裝得比較漂亮。\u003C\u002Fp>\u003Cul>\u003Cli>Agent 品質 = 模型能力 + 介面設計。\u003C\u002Fli>\u003Cli>工具呼叫會把問題變成系統協作。\u003C\u002Fli>\u003Cli>越複雜的框架，越容易藏 bug。\u003C\u002Fli>\u003Cli>標準化介面，能少寫很多接線碼。\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>AI 基礎設施不再只管 Serving\u003C\u002Fh2>\u003Cp>傳統 AI 基礎設施，重點是 serving。像是 batching、quantization、延遲控制、GPU 利用率。這些還是重要，但不夠了。\u003C\u002Fp>\u003Cp>Agent 會帶來第二層需求。系統要處理工具呼叫、狀態更新、重試、分支流程，甚至多個 worker 同時跑。這就不是單純的推論服務問題了。\u003C\u002Fp>\u003Cp>你可以把它想成三種成本一起冒出來。模型推論成本。協調成本。失敗重試成本。很多團隊只看前者，最後卻被後兩者拖垮。\u003C\u002Fp>\u003Cp>所以現在的 Agent infra，很像 runtime、workflow engine、資料協調層的混血。模型只是其中一塊。真正的產品價值，常常在模型外面。\u003C\u002Fp>\u003Cp>你可能會想問，那實作上要注意什麼？我整理成幾個很實際的點：\u003C\u002Fp>\u003Cul>\u003Cli>Agent 何時要 checkpoint 狀態。\u003C\u002Fli>\u003Cli>哪些動作要同步，哪些可背景執行。\u003C\u002Fli>\u003Cli>工具失敗後，怎麼重試才不會重複寫入。\u003C\u002Fli>\u003Cli>哪些資料能快取，哪些一定要重算。\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>MCP 把工具連接往標準化推\u003C\u002Fh2>\u003Cp>\u003Ca href=\"https:\u002F\u002Fmodelcontextprotocol.io\" target=\"_blank\" rel=\"noopener\">MCP\u003C\u002Fa> 在 2024 年 11 月公開後，重點不在名字。重點是，它試著把 Agent 和外部工具、外部資料的連接方式標準化。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775057795329-0l9o.png\" alt=\"Agent 基礎設施正在重寫 AI\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>這件事很實際。每多一個自訂 connector，就多一種 schema。多一種 auth 流程。多一種 tool description。多一種失敗模式。最後整個系統會變成一坨手工接線。\u003C\u002Fp>\u003Cp>MCP 的價值，就是讓開發者用一致的協定暴露能力。不是每個 app 都要跟每個 m\u003Ca href=\"\u002Fnews\u002Fclaude-code-march-2026-update-fixes-bugs-zh\">ode\u003C\u002Fa>l 單獨對接。這對想保留模型選擇權的團隊，很有感。\u003C\u002Fp>\u003Cp>它也會改變整合成本。內部工具如果能講同一種 protocol，團隊就少花時間改 adapter，多花時間調整 Agent 行為。這種看起來很無聊的基礎工作，往往才是能不能上線的差別。\u003C\u002Fp>\u003Cblockquote>“The future of AI is not about one model to rule them all. It is about many models, many tools, and a standard way for them to talk.” — \u003Ca href=\"https:\u002F\u002Fwww.anthropic.com\u002Fnews\u002Fmodel-context-protocol\" target=\"_blank\" rel=\"noopener\">Dario Amodei\u003C\u002Fa>\u003C\u002Fblockquote>\u003Cp>這句話很直白。價值中心，正在從模型存取，移到連接層。\u003C\u002Fp>\u003Ch2>狀態與排程變成第一級問題\u003C\u002Fh2>\u003Cp>Agent 一旦真的開始做事，state 就不再是細節。你要知道它看過什麼。試過什麼。哪些工具輸出可信。任務卡住後要從哪裡接回來。\u003C\u002Fp>\u003Cp>這會把 AI 系統往分散式系統工程拉。不是只有 LLM 問答。還有 checkpoint、recovery、task history、memory pressure。說真的，這些比 prompt engineering 更像正經工程。\u003C\u002Fp>\u003Cp>排程也一樣重要。單一 request 的 Agent，queue 也許就夠了。可是如果你跑上百個長壽命 Agent，就要管 prior\u003Ca href=\"\u002Fnews\u002Fgithub-ai-bug-detection-code-security-zh\">it\u003C\u002Fa>y、concurrency、worker 分配、工具衝突。\u003C\u002Fp>\u003Cp>這時候，Agent infra 通常會拆成四層：\u003C\u002Fp>\u003Cul>\u003Cli>\u003Cstrong>Serving\u003C\u002Fstrong>：推論、batching、延遲、成本。\u003C\u002Fli>\u003Cli>\u003Cstrong>State\u003C\u002Fstrong>：記憶、checkpoint、任務歷史、復原。\u003C\u002Fli>\u003Cli>\u003Cstrong>Scheduling\u003C\u002Fstrong>：佇列、worker、重試、平行執行。\u003C\u002Fli>\u003Cli>\u003Cstrong>Tooling\u003C\u002Fstrong>：connector、權限、schema、protocol。\u003C\u002Fli>\u003C\u002Ful>\u003Cp>這些方向也能從工具生態看出來。\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flanggraph\" target=\"_blank\" rel=\"noopener\">LangGraph\u003C\u002Fa> 主打 graph-based workflow。\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python\" target=\"_blank\" rel=\"noopener\">OpenAI Agents SDK\u003C\u002Fa> 則偏向結構化多步驟應用。路線不同，但方向很一致。\u003C\u002Fp>\u003Cp>再看數據比較，就更清楚了。傳統 LLM 服務，常常只看 latency 和 cost。Agent 系統還要多看三個指標：工具成功率、狀態恢復率、重試後完成率。少一個，產品就可能卡住。\u003C\u002Fp>\u003Cul>\u003Cli>傳統 serving：看 TPS、P95 latency、GPU 利用率。\u003C\u002Fli>\u003Cli>Agent infra：再加工具成功率、狀態恢復率。\u003C\u002Fli>\u003Cli>單次失敗的代價，常常高於一次推論費用。\u003C\u002Fli>\u003Cli>標準 protocol 會降低整合與維護成本。\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>這對現在的建置團隊代表什麼\u003C\u002Fh2>\u003Cp>如果你現在在做 Agent 產品，最直接的建議很簡單。不要再把模型當整個 stack。真正的差距，常常出現在協調失敗有沒有被處理好。\u003C\u002Fp>\u003Cp>工具契約要清楚。狀態要能持久化。流程要能重試。失敗要能復原。這些聽起來很土，但產品能不能穩，通常就卡在這裡。\u003C\u002Fp>\u003Cp>我也想吐槽一下。很多 Agent demo 很會秀。流程拉得很長。抽象層堆得很高。看起來像魔法。可是一進 production，就開始出現各種鬼故事。\u003C\u002Fp>\u003Cp>真正能活下來的系統，通常控制流很清楚。介面很明白。狀態很可追。不是因為它比較酷，是因為它比較不容易炸。\u003C\u002Fp>\u003Ch2>AI 工程正在往哪裡走\u003C\u002Fh2>\u003Cp>這波變化背後，其實是 AI 工程成熟化。早期大家在比模型分數。後來開始比推論成本。現在輪到 Agent 的協調層。\u003C\u002Fp>\u003Cp>這也很像雲端時代的演進。先是 VM。再來是容器。接著是編排。AI 也在走類似路線。模型還是核心，但真正拉開差距的，變成周邊系統設計。\u003C\u002Fp>\u003Cp>所以如果你是工程師、產品人、或創業者，現在該看的不是「哪個模型最強」。而是「哪個 Agent 架構最穩」。差別很大。\u003C\u002Fp>\u003Cp>我自己的判斷很直接。接下來 12 個月，會有更多團隊把重點放在 stateful runtime、protocol support、task orchestration。這些東西會比單純換更大的模型更有感。你如果還在只盯參數量，可能會錯過真正的戰場。\u003C\u002Fp>","SWE-agent、Anthropic 與 MCP 讓人看見，Agent 表現越來越取決於介面、狀態與排程，不再只看模型大小。","zhuanlan.zhihu.com","https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F2019347592367093406",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775057778098-qqk6.png",[13,14,15,16,17,18,19,20],"Agent infra","SWE-agent","Anthropic","MCP","AI 基礎設施","LLM","Agent","分散式系統","zh",1,false,"2026-04-01T10:06:26.981996+00:00","2026-04-01T10:06:26.841+00:00","done","06cc000d-ccf1-498f-8ed1-09554cefa825","agent-infra-rewrites-ai-infrastructure-zh","industry","d6e69428-99ef-4933-b892-87440d05e2b3","published","2026-04-09T09:00:54.237+00:00",[34,36,38,40,42,44,45],{"name":19,"slug":35},"agent",{"name":14,"slug":37},"swe-agent",{"name":16,"slug":39},"mcp",{"name":15,"slug":41},"anthropic",{"name":18,"slug":43},"llm",{"name":20,"slug":20},{"name":46,"slug":47},"agent infra","agent-infra",{"id":30,"slug":49,"title":50,"language":51},"agent-infra-rewrites-ai-infrastructure-en","Agent Infra Is Rewriting AI Infrastructure","en",[53,59,65,71,77,83],{"id":54,"slug":55,"title":56,"cover_image":57,"image_url":57,"created_at":58,"category":29},"e6379f8a-3305-4862-bd15-1192d3247841","why-nebius-ai-pivot-is-more-real-than-hype-zh","為什麼 Nebius 的 AI 轉型比炒作更真實","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778823044520-9mfz.png","2026-05-15T05:30:24.978992+00:00",{"id":60,"slug":61,"title":62,"cover_image":63,"image_url":63,"created_at":64,"category":29},"66c4e357-d84d-43ef-a2e7-120c4609e98e","nvidia-backs-corning-factories-with-billions-zh","Nvidia 出資 Corning 工廠擴產","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778822450270-trdb.png","2026-05-15T05:20:27.701475+00:00",{"id":66,"slug":67,"title":68,"cover_image":69,"image_url":69,"created_at":70,"category":29},"31d8109c-8b0b-46e2-86bc-d274a03269d1","why-anthropic-gates-foundation-ai-public-goods-zh","為什麼 Anthropic 和 Gates Foundation 應該投資 A…","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778796636474-u508.png","2026-05-14T22:10:21.138177+00:00",{"id":72,"slug":73,"title":74,"cover_image":75,"image_url":75,"created_at":76,"category":29},"17cafb6e-9f2c-43c4-9ba3-ef211d2780b1","why-observability-is-critical-cloud-native-systems-zh","為什麼可觀測性是雲原生系統的生存條件","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778794245143-tfqn.png","2026-05-14T21:30:25.97324+00:00",{"id":78,"slug":79,"title":80,"cover_image":81,"image_url":81,"created_at":82,"category":29},"2fb441af-d3c6-4af8-a356-a40b25a67c00","data-centers-pushing-homeowners-to-solar-zh","資料中心推升房主裝太陽能","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778793651300-gi06.png","2026-05-14T21:20:40.899115+00:00",{"id":84,"slug":85,"title":86,"cover_image":87,"image_url":87,"created_at":88,"category":29},"387bddd8-e5fc-4aa9-8d1b-43a34b0ece43","how-to-choose-gpu-for-yihuan-zh","怎麼選《异环》GPU","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778786461303-39mx.png","2026-05-14T19:20:29.220124+00:00",[90,95,100,105,110,115,120,125,130,135],{"id":91,"slug":92,"title":93,"created_at":94},"ee073da7-28b3-4752-a319-5a501459fb87","ai-in-2026-what-actually-matters-now-zh","2026 AI 真正重要的事","2026-03-26T07:09:12.008134+00:00",{"id":96,"slug":97,"title":98,"created_at":99},"83bd1795-8548-44c9-9a7e-de50a0923f71","trump-ai-framework-power-speech-state-preemption-zh","川普 AI 框架瞄準電力、言論與州權","2026-03-26T07:12:18.695466+00:00",{"id":101,"slug":102,"title":103,"created_at":104},"ea6be18b-c903-4e54-97b7-5f7447a612e0","nvidia-gtc-2026-big-ai-announcements-zh","NVIDIA GTC 2026 重點拆解","2026-03-26T07:14:26.62638+00:00",{"id":106,"slug":107,"title":108,"created_at":109},"4bcec76f-4c36-4daa-909f-54cd702f7c93","claude-users-spreading-out-and-getting-better-zh","Claude 用戶更分散，也更會用","2026-03-26T07:22:52.325888+00:00",{"id":111,"slug":112,"title":113,"created_at":114},"bd903b15-2473-4178-9789-b7557816e535","openclaw-raises-hard-question-for-ai-models-zh","OpenClaw 逼問 AI 模型價值","2026-03-26T07:24:54.707486+00:00",{"id":116,"slug":117,"title":118,"created_at":119},"eeac6b9e-ad9d-4831-8eec-8bba3f9bca6a","gap-google-gemini-checkout-fashion-search-zh","Gap 把結帳搬進 Gemini","2026-03-26T07:28:23.937768+00:00",{"id":121,"slug":122,"title":123,"created_at":124},"0740e53f-605d-4d57-8601-c10beb126f3c","google-pushes-gemini-transition-to-march-2026-zh","Google 把 Gemini 轉換延到 2026 年 3…","2026-03-26T07:30:12.825269+00:00",{"id":126,"slug":127,"title":128,"created_at":129},"e660d801-2421-4529-8fa9-86b82b066990","metas-llama-4-benchmark-scandal-gets-worse-zh","Meta Llama 4 分數風波又擴大","2026-03-26T07:34:21.156421+00:00",{"id":131,"slug":132,"title":133,"created_at":134},"183f9e7c-e143-40bb-a6d5-67ba84a3a8bc","accenture-mistral-ai-sovereign-enterprise-deal-zh","Accenture 攜手 Mistral AI 賣主權 AI","2026-03-26T07:38:14.818906+00:00",{"id":136,"slug":137,"title":138,"created_at":139},"191d9b1b-768a-478c-978c-dd7431a38149","mistral-ai-faces-its-hardest-year-yet-zh","Mistral AI 迎來最硬的一年","2026-03-26T07:40:23.716374+00:00"]