1.6 基础理论

flowchart TD %% --- 样式（安全） --- classDef env fill:#f7e8f0,stroke:#c2185b,stroke-width:2px,rx:12,ry:12,color:#111; classDef agent fill:#e8f7f0,stroke:#0f9d58,stroke-width:2px,rx:12,ry:12,color:#111; classDef comp fill:#e6f0fb,stroke:#1a73e8,stroke-width:1.5px,rx:8,ry:8,color:#111; classDef action fill:#fff5cc,stroke:#eab308,stroke-width:1.5px,rx:8,ry:8,color:#111; %% --- 环境 --- subgraph ENV["环境"] PERCEPTS["感知输入"] ACTIONS["动作"] end class ENV env %% --- 智能体 --- subgraph AG["AI 智能体"] S["传感器<br/>(输入、API、webhook)"] PERCEPTION["感知层<br/>(预处理、嵌入)"] KB["知识库 / 记忆<br/>(事实、向量、状态)"] REASON["推理引擎<br/>(LLM+提示词、规则、RL)"] PLAN["规划与目标<br/>(分解、调度)"] LEARN["学习模块<br/>(反馈、微调、RL)"] ACT["执行器<br/>(API、命令、输出)"] end class AG agent class S,PERCEPTION,KB,REASON,PLAN,LEARN,ACT comp %% --- 流程 --- PERCEPTS --> S --> PERCEPTION --> KB PERCEPTION --> REASON KB --> REASON REASON --> PLAN --> ACT LEARN --> KB LEARN --> REASON ACT --> ACTIONS