Agents & Autonomy

實務中的代理迴圈：ReAct、工具與失敗模式

多數關於 agent 的工程討論，太早亮出 agent 這個詞，卻太晚才談運營迴圈。其實實務上真正重要的設計問題很簡單：模型一旦能執行不止一步，系統怎麼決定下一步做什麼？能呼叫哪些工具？可以從結果推斷什麼？又該在何時停下來？

Agent Loops in Practice: ReAct, Tools, and Failure Modes

Most engineering discussions about agents start too early with the word agent and too late with the operational loop. In practice, the important design question is simpler: once a model can take more than one step, how does the system decide what to do next, what tools it may call, what it is all...

助理、工作流程與代理：為適當的自主層級而設計

Agent（代理）已經成為 AI 中最被濫用的術語之一。產品團隊拿它來形容各種東西——從帶有檢索功能的聊天介面，到可以自行規劃、呼叫工具和採取行動的長時間執行程式，通通都算。這種詞彙漂移會造成實際問題：真正的設計問題明明是架構性的，團隊卻在爭論標籤。

Assistants, Workflows, and Agents: Designing for the Right Level of Autonomy

Agent has become one of the most overloaded terms in AI. Product teams use it to describe everything from a chat interface with retrieval to a long-running process that can plan, call tools, and take actions on its own. That vocabulary drift creates a practical problem: teams start arguing about ...