# AgentVerse: exploring emergent behavior in multi-agent collaborations

Source: https://arxiv.org/abs/2308.10848
Kiwi News: https://news.kiwistand.com/stories/AgentVerse-exploring-emergent-behavior-in-multi-agent-collaborations?index=0x65075af8a13e682ec61ca9a67e43cc9b9b417f2c2387d059b93135e4d08f293fa774f344
Submitted by m-j-r.eth on 2023-09-17 UTC, 1 upvote, 0 comments

## Summary

Researchers including Weize Chen and Chen Qian propose AgentVerse, a multi-agent framework that dynamically adjusts its group composition to act as a system greater than the sum of its parts. Experiments show that groups deployed by the framework outperform a single agent. The authors also examine social behaviors that emerge among agents during collaborative tasks and discuss strategies to leverage positive behaviors and mitigate negative ones. Code is slated for release soon, though no date is given.

## Article

AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors

Authors: Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian, Yujia Qin, Xin Cong, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou

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{this https URL}.