Skip to yearly menu bar Skip to main content


AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors

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

Halle B #62
[ ] [ Project Page ]
Wed 8 May 1:45 a.m. PDT — 3:45 a.m. PDT


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. We will release our codebase, AgentVerse, to further facilitate multi-agent research.

Chat is not available.