Week 5: Multi-Agent Architectures

Communication topologies, AutoGen, MetaGPT, ChatDev

Week 5 of 12

Learning Objectives

  • Implement message passing between agents
  • Build coordination patterns
  • Design multi-agent workflows

Topics Covered

  • Multi-agent communication patterns
  • AutoGen framework
  • MetaGPT software development
  • Role-based agent teams

Resources

Jupyter Notebooks

Open Message Passing in Colab Message Passing Open Coordination Demo in Colab Coordination Demo

Required Readings

PaperAuthorsYearLink
AutoGen: Enabling Next-Gen LLM Applications Wu et al. 2023 arXiv
MetaGPT: Meta Programming for Multi-Agent Collaboration Hong et al. 2023 arXiv

Reading Guide: Multi-Agent Systems Survey

2-3 hours Multi-agent architectures Communication patterns Role specialization

Comprehensive survey of LLM-based multi-agent collaboration

Primary Paper

A Systematic Survey on Large Language Model-based Multi-Agent Collaboration
Tran, et al. (2025)
arXiv arXiv

Exercise: Multi-Agent Design

100 Points 5-7 hours Advanced

Design and implement multi-agent coordination

Learning Objectives

  • Create: Design multi-agent workflows
  • Apply: Implement message passing between agents
  • Analyze: Compare coordination patterns

Tasks

TaskPointsDescription
Agent Team Design 30 Design roles for a multi-agent team
Message Passing 40 Implement agent communication
Coordination Analysis 30 Measure coordination overhead

Exercise

Build a software development team simulation with:

  1. Product Manager agent
  2. Architect agent
  3. Developer agent
  4. Reviewer agent
  5. Coordinated workflow

Discussion Questions

  1. When is multi-agent better than single-agent?
  2. How do you handle conflicting agent outputs?
  3. What coordination patterns work best for different tasks?

Additional Resources

Discussion & Questions

Join the Conversation

Have questions about this week's material? Want to discuss concepts with fellow students?



Back to top