Walk through AutoGen GroupChat handoffs between UserProxyAgent and AssistantAgent

Flashcard·Medium·4.0 · 0·~30s·Asked atMicrosoft NVIDIA OpenAI

Attempt it

The GroupChatManager picks the next speaker (via its select_speaker policy. Round-robin, LLM-driven, or custom). The UserProxyAgent posts the human message; the manager selects the AssistantAgent next. The AssistantAgent emits either text or a tool call. If it is a tool call, the manager hands control back to the UserProxyAgent, which is configured to execute code/tools locally (or ask the human via human_input_mode). The execution result is posted as the UserProxy's next message; the manager re-selects the assistant, which reads the tool output and produces the final reply. The conversation history is shared across all agents in the chat, there is no private channel, and the manager keeps looping until a termination condition fires.

Your answer

Quick reference

TL;DR

AutoGen routes every turn through a GroupChatManager whose select_speaker policy chooses the next agent; the UserProxyAgent doubles as the human stand-in and the tool executor.

Memory aid

Easy to grasp

Picture a small meeting with a chairperson, a question-asker, and an expert. The chairperson never answers questions. They just point at whoever should speak next. The question-asker raises their hand and asks something. The chair points at the expert. The expert says, 'I need to look that up in the filing cabinet first,' so the chair points back at the question-asker, who in this room is also the person who can open the cabinet. They read out what they found, the chair points at the expert again, and the expert gives the final answer. Everyone hears every word; nothing is whispered. The meeting ends when someone says the magic stop phrase.

Key concepts

LLM frameworks Agents

Detailed answer & concept explanation

~5 min read

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.

Quick scan · 2–4 min

Everything important, quickly.

5 minutes: who the manager is, what select_speaker does, why the UserProxy owns tool execution, and how termination is wired.

Code example

python

from autogen import AssistantAgent, UserProxyAgent, GroupChat, GroupChatManager

assistant = AssistantAgent(
    name="assistant",
    llm_config={"model": "claude-sonnet-4-6"},
)
user = UserProxyAgent(
    name="user",
    human_input_mode="NEVER",
    code_execution_config={"work_dir": "runs", "use_docker": True},
    is_termination_msg=lambda m: "TERMINATE" in m.get("content", ""),
)

chat = GroupChat(agents=[user, assistant], messages=[], max_round=12)
manager = GroupChatManager(groupchat=chat, llm_config={"model": "gpt-5.5"})

user.initiate_chat(manager, message="Compute the SHA-256 of 'autogen'. End with TERMINATE.")

Real-world examples

Real products, models, and research that use this idea.

Microsoft Research's original AutoGen paper, which introduced GroupChat as a generalisation of two-agent chat for conversable multi-agent programs.
AutoGen Studio (the no-code UI shipped by the AutoGen team) exposes the speaker-selection policy directly as a dropdown, illustrating how central the routing primitive is.
Production deployments commonly pair AutoGen GroupChats with Claude Sonnet 4.6 or GPT-5.5 as the AssistantAgent's underlying model, and a cheaper model as the LLM-driven speaker selector.
The AutoGen GitHub `notebook/agentchat_groupchat.ipynb` example is the canonical reference implementation of this exact UserProxy + Assistant loop.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QHow would you implement a custom select_speaker that always routes tool outputs back to the assistant?

QWhat happens if two agents both can execute code and the manager picks the wrong one for a tool call?

QHow does GroupChat differ from AutoGen's nested_chat, and when do you mix them?

Don't say this

Red flags and common mistakes that signal junior thinking. Click to expand.

Most common mistake

Treating the UserProxyAgent as only the human relay and forgetting it is also the side that runs tool calls. So disabling code execution silently breaks every tool-using turn.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

References

Primary sources. Skim if you want the original framing.