Autogen Multi Agent Teams

RoundRobinGroupChat with participants=[planner, coder, reviewer]. Operator expects planner→coder→reviewer→planner alternation but observes planner speaking twice in a row when coder emits an empty response.

RoundRobinGroupChat advances strictly through participants in declared order — empty agent responses still count as that agent's turn. If a 'speak again' is needed, either re-prompt within the same turn or switch to SelectorGroupChat with allow_repeated_speaker. Do not rely on side effects to skip …

SelectorGroupChat with selector_prompt that references participant names but each participant's description= is left blank. Selector LLM picks the same agent every turn.

Selector picks the next speaker using participant.description — populate each agent's description with a one-sentence capability statement (e.g. 'researcher: web search and fact extraction'). Without descriptions the selector has nothing to disambiguate on and degenerates to a single speaker.

SelectorGroupChat with allow_repeated_speaker=False. Selector LLM picks the same agent that just spoke.

With allow_repeated_speaker=False, AutoGen re-asks the selector (or falls back to a different participant) so the same speaker cannot speak twice in a row. Verify the actual transcript respects this by inspecting the message source field. To permit the same agent to refine its own answer, set allow…