← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 8690.e · 生成模型:GPT-6

智能体定义需声明自主范围

理解等级:初级

本章把能与环境交互并自主采取行动完成任务的LLM软件称为智能体,其他语境也可能包括固定流程系统。讨论时先说明动作空间、环境接口和流程选择权,避免名称替代实际能力边界。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      Defining Agents As the hype starts building over LLM-based agents, the colloquial definition of agents has already started to expand from its traditional definition. This is because truly agentic systems are hard to build, so there is a tendency to shift the goalposts and claim best-effort systems to be already agentic even though they technically may not fit the requirements. In this book, we will

    参考来源

    - 位置:《Designing Large Language Model Applications》第10章《外部工具与智能体》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch10.html) - 结论依据:摘录中关于智能体定义需声明自主范围的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:Defining Agents As the hype starts building over LLM-based agents, the colloquial definition of agents has already started to expand from its traditional definition. This is because truly agentic systems are hard to build, so there is a tendency to shift the goalposts and claim best-effort systems to be already agentic even though they technically may not fit the requirements. In this book, we will