AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
This addresses the need for efficient multi-agent cooperation in AI systems, though it appears incremental as it builds on existing LLM-based agents.
The paper tackles the problem of enabling multiple autonomous agents to collaborate effectively in real-world tasks, proposing a framework that dynamically adjusts agent composition and demonstrating that multi-agent groups outperform single agents.
Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks. However, in real-world scenarios, cooperation among individuals is often required to enhance the efficiency and effectiveness of task accomplishment. Hence, inspired by human group dynamics, we propose a multi-agent framework \framework that can collaboratively and dynamically adjust its composition as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that \framework framework can effectively deploy multi-agent groups that outperform a single agent. Furthermore, we delve into the emergence of social behaviors among individual agents within a group during collaborative task accomplishment. In view of these behaviors, we discuss some possible strategies to leverage positive ones and mitigate negative ones for improving the collaborative potential of multi-agent groups. Our codes for \framework will soon be released at \url{https://github.com/OpenBMB/AgentVerse}.