AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
Weize Chen1 , Yusheng Su1∗, Jingwei Zuo1, Cheng Yang3🖂, Chenfei Yuan1, Chi-Min Chan1, Heyang Yu1, Yaxi Lu1, Yi-Hsin Hung2, Chen Qian1, Yujia Qin1, Xin Cong1, Ruobing Xie4, Zhiyuan Liu1🖂, Maosong Sun1, Jie Zhou4 1 Department of Computer Science and Technology, Tsinghua University 2 School of Economics and Management, Tsinghua University 3 School of Computer Science, Beijing University of Posts and Telecommunications 4 Pattern Recognition Center, WeChat AI, Tencent Inc. The first two authors contributed equally. 🖂 Corresponding author.
Abstract
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 AgentVerse that can effectively orchestrate a collaborative group of expert agents as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that AgentVerse can proficiently deploy multi-agent groups that outperform a single agent. Extensive experiments on text understanding, reasoning, coding, tool utilization, and embodied AI confirm the effectiveness of AgentVerse. Moreover, our analysis of agent interactions within AgentVerse reveals the emergence of specific collaborative behaviors, contributing to heightened group efficiency. Our code has been released at https://github.com/OpenBMB/AgentVerse/.
中文速览
让大语言模型（LLM）驱动的智能体独自应对复杂任务往往力不从心，而现实中的难题通常需要多人协作才能高效解决。受人类团队协作规律的启发，研究者提出了多智能体框架 AgentVerse，将问题求解过程拆分为"专家招募、协作决策、行动执行、效果评估"四个循环迭代的阶段，并允许根据任务进展动态调整智能体团队的构成与角色分工。在文本理解、推理、编程、工具调用和具身AI（Embodied AI）等多项实验中，AgentVerse 组建的多智能体群组均明显优于单个智能体，且在协作过程中自发涌现出"主动帮扶""从众纠偏"等类人社会行为。这项工作为构建更通用、更自适应的智能体协作系统提供了可行路径，也揭示了多智能体协作中潜在的风险（如错误信息的传播放大），对推动 AGI 研究具有重要参考价值。
原文 arXiv:2308.10848;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2308.10848v3