[Feature Request] Multi agent Workforce

[Wendong-Fan]

Required prerequisites

• [X] I have searched the Issue Tracker and Discussions that this hasn't already been reported. (+1 or comment there if it has.)
• [ ] Consider asking first in a Discussion.

Motivation

Workforce support mulit agent communication, user can add as much agent as they want into this Workforce

Solution

one special agent can be designed to manage the chat and decide which agent be the next speaker need more study to see if there's better design

Alternatives

No response

Additional context

No response

[Wendong-Fan]

1. Workforce(task="Human Task",society=[Agent A, Agent B, RolePlaying …..],manager_agent_config={…}, task_agent_config={…},… workforce = [], description=”xx”)→ ChatResult & Message
2. Guohao: Workforce(task=””, workforce=[workforce, …])
3. Agents in Workforce
   1. Manager Agent(optional): track task and can create new agent
   2. Task Agent(optional): Specify, Spilt, Generate, Plan tasks, already supported in CAMEL
   3. Critic Agent(optional): Assists in selecting an option, already supported in CAMEL

4. Flow in Workforce

   1. Human Task → Task A, Task B, Task C (Message) by Task Agent

   2. Manager Agent initialize the first round task assignment

      Task A -> Agent A (model=Model A, tool=[T1, T2],knowledgebase=[KB1, KB2]) Task B -> Agent B (model=Model B, tool=[T1, T3, T5],knowledgebase=[KB2, KB3, KB4]) Task C ....

   3. environment for Agent A = related tasks information + all agents information environment for Manager Agent = all tasks information + all agents information

   4. If Agent A can solve task A, CAMEL Task A done, back to Manager Agent.

      If Agent A can’t solve task A, Agent A will ask Task Agent split Task A, make it into Task A.1, Task A.2…, from Agent A’s environment information, Agent A find another agent can solve Task A.1, send message to that Agent, assign Task A.1, once finished ,back to Manager Agent.

      Society pipeline? sequential, hierarchical, star, or other topology..

      Task A.1 → Workforce with 3 agents