// ⌘ Agents & Tool Use
Multi-Agent Conversation (AutoGen)
Multiple specialised LLM agents converse and call tools to solve a task together.
多智能体对话框架（AutoGen） aka Multi-Agent / 多智能体 2023 Foundational core
IN PLAIN WORDS
Give each agent a role – coder, reviewer, executor, human proxy – and let the task progress through their messages, calling tools or a human when needed. It turned multi-agent collaboration into programmable conversation patterns and became a reference for later multi-agent frameworks.
Used in: Multi-agent coding, data analysis and research-assistant prototypes
TIMELINE · prerequisites → this → what builds on it
01Original paper
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
Qingyun Wu, Gagan Bansal, Jieyu Zhang, et al. · 2023
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Then you can learn
- Nothing in the atlas builds on it yet
Related:Generative Agents (Memory & Reflection)Model Context Protocol (MCP)
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-22.
- JSON: /api/learn/algorithms.json (id:
autogen)