https://www.hansking.cn/blog A posts created with Next.js and Tailwind.css en-us admin@hansking.cn (HANS) admin@hansking.cn (HANS) Sun, 30 Mar 2025 10:00:00 GMT https://www.hansking.cn/blog/2026/Agent-shi-shen-me-mo-xing-gong-ju-zhuang-tai-yu-xun-huan https://www.hansking.cn/blog/2026/Agent-shi-shen-me-mo-xing-gong-ju-zhuang-tai-yu-xun-huan [{"value":"Agent 是什么：模型、工具、状态与循环","url":"#agent-是什么模型工具状态与循环","depth":1},{"value":"一、先区分聊天机器人、工作流和 Agent","url":"#一先区分聊天机器人工作流和-agent","depth":2},{"value":"二、Agent 的四个基本零件","url":"#二agent-的四个基本零件","depth":2},{"value":"1. 模型：负责理解和选择","url":"#1-模型负责理解和选择","depth":3},{"value":"2. 工具：连接真实世界","url":"#2-工具连接真实世界","depth":3},{"value":"3. 状态：记住任务走到哪里","url":"#3-状态记住任务走到哪里","depth":3},{"value":"4. 循环：让结果影响下一步","url":"#4-循环让结果影响下一步","depth":3},{"value":"三、把 Agent 写成一个可观察的状态机","url":"#三把-agent-写成一个可观察的状态机","depth":2},{"value":"四、最小 Agent 循环","url":"#四最小-agent-循环","depth":2},{"value":"五、计划不是越详细越好","url":"#五计划不是越详细越好","depth":2},{"value":"六、工具调用时，模型只是在提议","url":"#六工具调用时模型只是在提议","depth":2},{"value":"七、记忆不等于把所有聊天记录塞回去","url":"#七记忆不等于把所有聊天记录塞回去","depth":2},{"value":"八、Agent 的失败不是一种失败","url":"#八agent-的失败不是一种失败","depth":2},{"value":"九、怎么评测一个 Agent","url":"#九怎么评测一个-agent","depth":2},{"value":"十、我的总结：自主性必须和边界一起增长","url":"#十我的总结自主性必须和边界一起增长","depth":2}] Sun, 30 Mar 2025 10:00:00 GMT admin@hansking.cn (HANS) AILLMAgent架构学习top https://www.hansking.cn/blog/2026duo-zhi-neng-ti-xie-zuo-shen-me-shi-hou-zhi-de-chai-cheng-duo-ge-Agent https://www.hansking.cn/blog/2026duo-zhi-neng-ti-xie-zuo-shen-me-shi-hou-zhi-de-chai-cheng-duo-ge-Agent [{"value":"多智能体协作：什么时候值得拆成多个 Agent","url":"#多智能体协作什么时候值得拆成多个-agent","depth":1},{"value":"一、先问一个不太讨喜的问题：单 Agent 真的不够吗","url":"#一先问一个不太讨喜的问题单-agent-真的不够吗","depth":2},{"value":"二、什么情况下拆分确实有价值","url":"#二什么情况下拆分确实有价值","depth":2},{"value":"1. 任务有天然的专业边界","url":"#1-任务有天然的专业边界","depth":3},{"value":"2. 不同环节需要不同权限","url":"#2-不同环节需要不同权限","depth":3},{"value":"3. 某些工作可以并行","url":"#3-某些工作可以并行","depth":3},{"value":"4. 需要相互质疑，而不是只需要多写一遍","url":"#4-需要相互质疑而不是只需要多写一遍","depth":3},{"value":"三、四种常见协作模式","url":"#三四种常见协作模式","depth":2},{"value":"顺序流水线：一个接一个传递结果","url":"#顺序流水线一个接一个传递结果","depth":3},{"value":"并行专家：多个 Agent 同时给出独立意见","url":"#并行专家多个-agent-同时给出独立意见","depth":3},{"value":"监督者—执行者：负责规划与执行分离","url":"#监督者执行者负责规划与执行分离","depth":3},{"value":"辩论与裁决：不同假设之间互相挑战","url":"#辩论与裁决不同假设之间互相挑战","depth":3},{"value":"四、协作的核心不是聊天，而是共享状态","url":"#四协作的核心不是聊天而是共享状态","depth":2},{"value":"五、消息协议要小，结果要能验证","url":"#五消息协议要小结果要能验证","depth":2},{"value":"六、失败恢复比角色数量更值得设计","url":"#六失败恢复比角色数量更值得设计","depth":2},{"value":"七、如何判断拆分没有成功","url":"#七如何判断拆分没有成功","depth":2},{"value":"八、我的结论：把 Agent 当成有边界的同事","url":"#八我的结论把-agent-当成有边界的同事","depth":2}] Sun, 11 May 2025 10:00:00 GMT admin@hansking.cn (HANS) AILLMAgent多智能体架构 https://www.hansking.cn/blog/2026duo-mo-xing-lu-you-an-zhi-liang-yan-chi-he-jia-ge-xuan-ze-mo-xing https://www.hansking.cn/blog/2026duo-mo-xing-lu-you-an-zhi-liang-yan-chi-he-jia-ge-xuan-ze-mo-xing [{"value":"多模型路由：按质量、延迟和价格选择模型","url":"#多模型路由按质量延迟和价格选择模型","depth":1},{"value":"一、先把模型调用从业务代码里拿出来","url":"#一先把模型调用从业务代码里拿出来","depth":2},{"value":"二、先定义“什么叫合适”","url":"#二先定义什么叫合适","depth":2},{"value":"三、路由策略从简单规则开始","url":"#三路由策略从简单规则开始","depth":2},{"value":"四、加权评分适合处理多个目标","url":"#四加权评分适合处理多个目标","depth":2},{"value":"五、故障时的降级不是“随便换一个模型”","url":"#五故障时的降级不是随便换一个模型","depth":2},{"value":"六、熔断器保护整个服务","url":"#六熔断器保护整个服务","depth":2},{"value":"七、质量路由需要真实评测数据","url":"#七质量路由需要真实评测数据","depth":2},{"value":"八、成本控制要看“每个成功任务”","url":"#八成本控制要看每个成功任务","depth":2},{"value":"九、数据边界应该在路由前执行","url":"#九数据边界应该在路由前执行","depth":2},{"value":"十、流式响应让路由更难一点","url":"#十流式响应让路由更难一点","depth":2},{"value":"十一、不要过早训练一个“智能路由器”","url":"#十一不要过早训练一个智能路由器","depth":2},{"value":"十二、我的总结：路由系统是在管理取舍","url":"#十二我的总结路由系统是在管理取舍","depth":2}] Sun, 24 Nov 2024 10:00:00 GMT admin@hansking.cn (HANS) AILLM模型路由架构成本优化