VI · Multi-AgentEmerging★

Conversational Multi-Agent

also known as AutoGen Conversation, Two-Agent Conversation

Have agents converse turn by turn until a completion criterion fires; agent roles drive the conversation forward.

Context

A team is building an agent system whose task is naturally shaped like a conversation between two or more specialists: a coder agent and a reviewer agent revising a patch together, a teacher agent and a student agent working through an explanation, a writer agent and an editor agent. The work converges through back-and-forth rather than through a single agent's monologue.

Problem

A single-agent loop has nowhere to put the dialogue: there is no opposing voice to push back, and inner-monologue self-critique tends to agree with itself. A rigid orchestration pipeline that fixes the step order in advance over-prescribes the flow and removes the conversational dynamics that make the pairing valuable in the first place. Without a structure for turn-taking, the team is forced to choose between a flat solo loop and a brittle hard-coded sequence.

Forces

  • Turn allocation across agents.
  • Termination criterion definition.
  • Conversation can drift without supervision.

Example

A finance team wants an agent that drafts an internal memo, has a 'reviewer' poke holes in it, and revises until the reviewer signs off. A linear pipeline can't represent the back-and-forth, and a free-form group chat is too loose. They use an AutoGen-style conversational setup: a writer agent and a reviewer agent take turns until the reviewer emits an explicit approval token. Each turn drives the next; the loop ends when the role-defined criterion fires.

Diagram

Solution

Therefore:

Define agents with system prompts and allowed actions. Implement a conversation manager that selects which agent speaks next (round-robin, condition-based, model-decided). Each agent reads the conversation and emits a turn. Continue until termination criterion (task complete, max turns, explicit handoff to user).

What this pattern forbids. Each agent's outputs must conform to its role's allowed action set; agents may not act outside their role's vocabulary.

And the patterns that stand alongside it, or against it —

  • complementsRole Assignment★★— Assign each agent a named role (researcher, writer, critic, planner) with a role-specific prompt, tool palette, and acceptance criteria.
  • alternative-toSupervisor★★— Place a coordinating agent above a set of specialised agents and route work to them.
  • alternative-toCAMEL Role-Playing·— Have two agents role-play a user-assistant interaction to autonomously complete a task neither could solve alone.
  • alternative-toActor-Model Agents★— Implement each agent as an independent actor with its own mailbox, processing asynchronous messages one at a time and never sharing mutable state with peers.
  • complementsGroup-Chat Manager★★— Place a dedicated manager between the participants of a multi-agent group chat that decides which participant speaks next on each turn.

Neighbourhood

Click any neighbour to follow the language. Scroll to zoom, drag to pan.

Used in frameworks

References

Provenance