microsoft/autogen

[Python] SelectorGroupChat to support concurrent speakers

Open

#5395 opened on Feb 6, 2025

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Python (58,033 stars) (8,759 forks)batch import
help wantedproj-agentchat

Description

SelectorGroupChat can support concurrent speakers by choosing multiple speakers at once, and have the manager waiting for all the selected speakers to respond before selecting the next round of speakers.

Related discussion: #5364

Contributor guide

Tech stack
python
Domain
aibackend
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
Python basicsAutoGen frameworkSelectorGroupChat class
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60
Research direction
The issue requests extending SelectorGroupChat to support concurrent speakers. Start by reading the related discussion in #5364 to understand the desired behavior. Then examine the SelectorGroupChat implementation (likely in autogen/agentchat/groupchat.py) to see how speakers are currently selected one at a time. The goal is to modify the selection logic to allow multiple speakers and coordinate their responses. Look for existing tests for SelectorGroupChat to understand expected outcomes. Consider using asyncio.gather to wait for all selected speakers before proceeding.