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

TL;DR

The paper introduces the Internet of Agents (IoA), a flexible framework enabling heterogeneous LLM-based agents to collaborate effectively across distributed environments, surpassing existing multi-agent systems in adaptability and performance.

Contribution

The paper presents IoA, a novel scalable framework with an agent integration protocol and dynamic conversation control, facilitating seamless multi-agent collaboration across diverse environments.

Findings

IoA outperforms state-of-the-art baselines in various tasks.

It enables effective collaboration among heterogeneous agents.

The framework demonstrates scalability and adaptability in complex scenarios.

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 \url{https://github.com/OpenBMB/IoA}.