Multi-agent LLM system architecture

提示词

Landscape 16:9 high-fidelity systems figure of a multi-agent LLM architecture, in the style of a richly detailed AutoGen / LangGraph / Anthropic Managed Agents Figure 1. Subtle drop-shadows, warm-copper highlights, numbered flow markers ①②③④.

ZONE 1 — "User interface": rounded user box with placeholder task "research question: summarize recent red-teaming attacks and reproduce the top three".

ZONE 2 — "Orchestrator layer": central hexagonal hub "Planner LLM" with warm-copper top edge. Three satellite chips: "Task decomposition", "Agent routing", "Re-plan on failure". Small inset chip "prompt cache hit ~98%".

ZONE 3 — "Specialised workers": 2×2 hexagons "Researcher" / "Coder" / "Critic" / "Writer", each with glyph + status ribbon ("idle", "running step 3/5", "done", "running step 2/4"). Centre labeled "async message bus".

ZONE 4 — "Tools & memory": (a) "Tool registry" panel listing "web_search ×41", "python_exec ×27", "read_file ×18", "write_file ×12", "browser_use ×7"; (b) "Memory" panel with "Short-term scratchpad" and cylinder "Long-term vector store — 1.8M episodes".

Bottom inset "Example trace": 8-step horizontal timeline chips from "User asks" through "Planner decomposes", "Researcher: web_search(...)", "Coder: python_exec(...)", "Critic: verify", "Re-plan" (loop-back arrow), "Writer: compose final answer".

Title: "Agentic LLM system: planner orchestrates specialised workers over a shared tool and memory layer". Subtitle: "adapted from AutoGen (Wu et al., 2023), LangGraph, and Anthropic Managed Agents patterns".

中文译文

16:9 横版高保真系统图，展示多智能体 LLM 架构，风格参照细节丰富的 AutoGen / LangGraph / Anthropic Managed Agents Figure 1。细腻的投影，暖铜色高光，编号流程标记 ①②③④。

区域 1 —“用户界面”：圆角用户框，占位任务为“研究问题：总结近期的红队攻击并复现其中排名前三的攻击”。

区域 2 —“编排层”：中央六边形枢纽“Planner LLM”，顶部边缘为暖铜色。三个卫星标签块：“任务分解”、“智能体路由”、“失败后重新规划”。小型内嵌标签“prompt 缓存命中率约 98%”。

区域 3 —“专用执行者”：2×2 六边形“Researcher”/“Coder”/“Critic”/“Writer”，每个都带图标 + 状态条（“空闲”、“运行第 3/5 步”、“完成”、“运行第 2/4 步”）。中心标注“异步消息总线”。

区域 4 —“工具与记忆”：（a）“工具注册表”面板，列出“web_search ×41”、“python_exec ×27”、“read_file ×18”、“write_file ×12”、“browser_use ×7”；（b）“记忆”面板，包含“短期草稿区”和圆柱体“长期向量存储 — 180 万条 episode”。

底部内嵌“示例轨迹”：8 步横向时间轴标签块，从“用户提问”到“Planner 分解”、“Researcher: web_search(...)”、“Coder: python_exec(...)”、“Critic: 校验”、“重新规划”（回环箭头）、“Writer: 撰写最终答案”。

标题：“智能体式 LLM 系统：规划器在共享的工具与记忆层之上编排专用执行者”。副标题：“改编自 AutoGen（Wu et al., 2023）、LangGraph 与 Anthropic Managed Agents 的模式”。

溯源

原作者: wuyoscar
收录来源: wuyoscar/GPT-Image2-Skill · 82 · MIT