Category 1: Multi-agent infrastructure

• How to efficiently enable multi-agent interactions?
  • Generative Agents: Interactive Simulacra of Human Behavior

Category 2: Multi-agent safety and security

• What novel failure modes occur in multi-agent systems?
  • Analyze collusion between agents or correlated failures among agents
  • [2308.01404] Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models
  • [2402.07510] Secret Collusion Among Generative AI Agents
  • [2404.00806] Algorithmic Collusion by Large Language Models