Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence
Weize Chen, Ziming You, Ran Li, Yitong Guan, Chen Qian, Chenyang Zhao, Cheng Yang, Ruobing Xie, Zhiyuan Liu, Maosong Sun
2024-07-10
Summary
This paper talks about the Internet of Agents (IoA), a new framework designed to improve how different AI agents work together. It allows these agents to communicate and collaborate more effectively, similar to how people interact on the internet.
What's the problem?
The main problem is that current systems for managing multiple AI agents often struggle to integrate different types of agents, especially those created by different developers. Many existing frameworks are limited because they only work on one device and use fixed communication methods, making it hard for them to adapt to new tasks or environments.
What's the solution?
To solve these issues, the authors introduced IoA, which provides a flexible and scalable platform for collaboration among various AI agents. IoA includes an agent integration protocol that allows different agents to connect and communicate easily, much like how instant messaging apps work. It also features dynamic mechanisms for forming teams and managing conversations, enabling agents to work together more efficiently. The authors conducted extensive tests and found that IoA outperformed other systems in various tasks, showing its effectiveness in facilitating collaboration among diverse agents.
Why it matters?
This research is important because it represents a significant advancement in how AI systems can work together. By creating a framework that allows different agents to collaborate seamlessly, IoA has the potential to enhance many applications, such as customer support, healthcare, education, and autonomous driving. This could lead to smarter and more capable AI systems that can tackle complex problems more effectively.
Abstract
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 https://github.com/OpenBMB/IoA.