arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.07061cs.CL
收藏

Internet of Agents:编织异构智能体网络以实现协同智能

Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence

Tsinghua University(清华大学);Peking University(北京大学);Beijing University of Posts and Telecommunications(北京邮电大学);Tencent(腾讯)

Weize Chen, Ziming You, Ran Li, Yitong Guan, Chen Qian, Chenyang Zhao, Cheng Yang, Ruobing Xie, Zhiyuan Liu, Maosong Sun

AI总结:

针对现有多智能体框架难整合第三方智能体、难适配分布式环境及动态任务的问题,提出IoA框架,通过集成协议、类即时通讯架构等实现异构智能体协作,在多类基准上性能优于现有最优方法。

摘要:

大语言模型(LLMs)的快速发展为高能力自主智能体的开发铺平了道路。然而,现有的多智能体框架由于依赖自身生态系统内定义的智能体,往往难以整合各类有能力的第三方智能体。它们在模拟分布式环境方面也面临挑战,因为大多数框架仅限于单设备设置。此外,这些框架通常依赖硬编码的通信管道,限制了其对动态任务需求的适应性。受互联网概念的启发,我们提出了Internet of Agents(IoA,智能体互联网),这是一个新颖的框架,通过为基于LLM的多智能体协作提供灵活可扩展的平台来解决这些局限性。IoA引入了智能体集成协议、类即时通讯的架构设计,以及智能体组队和对话流控制的动态机制。通过在通用助手任务、具身AI任务和检索增强生成基准上的大量实验,我们证明IoA始终优于当前最优基线,展现了其促进异构智能体之间有效协作的能力。IoA代表了在类互联网环境中连接各类智能体的一步,在该环境中智能体可以无缝协作以实现更强的智能与能力。我们的代码库已发布于https://github.com/OpenBMB/IoA。

英文摘要:

The rapid advancement of large language models (LLMs) has paved the way for the development of highly capable autonomous agents. However, existing multi-agent frameworks often struggle with integrating diverse capable third-party agents due to reliance on agents defined within their own ecosystems. They also face challenges in simulating distributed environments, as most frameworks are limited to single-device setups. Furthermore, these frameworks often rely on hard-coded communication pipelines, limiting their adaptability to dynamic task requirements. Inspired by the concept of the Internet, we propose the Internet of Agents (IoA), a novel framework that addresses these limitations by providing a flexible and scalable platform for LLM-based multi-agent collaboration. IoA introduces an agent integration protocol, an instant-messaging-like architecture design, and dynamic mechanisms for agent teaming and conversation flow control. Through extensive experiments on general assistant tasks, embodied AI tasks, and retrieval-augmented generation benchmarks, we demonstrate that IoA consistently outperforms state-of-the-art baselines, showcasing its ability to facilitate effective collaboration among heterogeneous agents. IoA represents a step towards linking diverse agents in an Internet-like environment, where agents can seamlessly collaborate to achieve greater intelligence and capabilities. Our codebase has been released at \url{https://github.com/OpenBMB/IoA}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑