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".
한국어 번역
멀티 에이전트 LLM 아키텍처의 가로 16:9 고충실도 시스템 그림, 풍부하게 상세한 AutoGen / LangGraph / Anthropic Managed Agents Figure 1 스타일. 은은한 드롭 섀도, 따뜻한 구리색 하이라이트, 번호가 매겨진 흐름 마커 ①②③④.
ZONE 1 — "User interface": 자리 표시자 작업 "research question: summarize recent red-teaming attacks and reproduce the top three"가 있는 둥근 사용자 상자.
ZONE 2 — "Orchestrator layer": 따뜻한 구리색 상단 모서리를 가진 중앙 육각형 허브 "Planner LLM". 세 개의 위성 칩: "Task decomposition", "Agent routing", "Re-plan on failure". 작은 삽입 칩 "prompt cache hit ~98%".
ZONE 3 — "Specialised workers": 2×2 육각형 "Researcher" / "Coder" / "Critic" / "Writer", 각각 글리프 + 상태 리본("idle", "running step 3/5", "done", "running step 2/4"). 중앙에 "async message bus" 레이블.
ZONE 4 — "Tools & memory": (a) "web_search ×41", "python_exec ×27", "read_file ×18", "write_file ×12", "browser_use ×7"을 나열하는 "Tool registry" 패널; (b) "Short-term scratchpad"와 실린더 "Long-term vector store — 1.8M episodes"가 있는 "Memory" 패널.
하단 삽입 "Example trace": "User asks"에서 시작해 "Planner decomposes", "Researcher: web_search(...)", "Coder: python_exec(...)", "Critic: verify", "Re-plan"(되돌아가는 화살표), "Writer: compose final answer"로 이어지는 8단계 수평 타임라인 칩.
제목: "에이전트형 LLM 시스템: 플래너가 공유 도구 및 메모리 계층 위에서 전문화된 워커를 조율". 부제: "AutoGen(Wu et al., 2023), LangGraph 및 Anthropic Managed Agents 패턴에서 각색".
