AgentScope中的大规模多智能体模拟

Very Large-Scale Multi-Agent Simulation in AgentScope

July 25, 2024

作者: Xuchen Pan, Dawei Gao, Yuexiang Xie, Zhewei Wei, Yaliang Li, Bolin Ding, Ji-Rong Wen, Jingren Zhou

cs.AI

摘要

最近大型语言模型（LLMs）的进展为在非常大规模模拟中应用多智能体系统开辟了新途径。然而，在使用现有平台进行多智能体模拟时仍存在一些挑战，如可伸缩性有限、效率低、智能体多样性不足以及管理流程繁琐。为解决这些挑战，我们为AgentScope开发了几项新功能和组件，这是一个用户友好的多智能体平台，增强了其便利性和灵活性，以支持非常大规模的多智能体模拟。具体来说，我们提出了基于actor的分布式机制作为底层技术基础，实现了很高的可伸缩性和效率，并为模拟各种真实场景提供了灵活的环境支持，实现了多智能体的并行执行、集中式工作流编排，以及智能体之间以及智能体与环境之间的交互。此外，我们在AgentScope中集成了易于使用的可配置工具和自动生成后台管道，简化了创建具有多样化且详细背景设置的智能体的过程。最后，我们提供了一个基于Web的界面，方便监视和管理可能部署在多个设备上的大量智能体。我们进行了全面的模拟，以展示在AgentScope中提出的增强功能的有效性，并提供详细的观察和讨论，以突显在大规模模拟中应用多智能体系统的巨大潜力。源代码已在GitHub上发布，网址为https://github.com/modelscope/agentscope，以激发对大规模多智能体模拟的进一步研究和开发。

English

Recent advances in large language models (LLMs) have opened new avenues for applying multi-agent systems in very large-scale simulations. However, there remain several challenges when conducting multi-agent simulations with existing platforms, such as limited scalability and low efficiency, unsatisfied agent diversity, and effort-intensive management processes. To address these challenges, we develop several new features and components for AgentScope, a user-friendly multi-agent platform, enhancing its convenience and flexibility for supporting very large-scale multi-agent simulations. Specifically, we propose an actor-based distributed mechanism as the underlying technological infrastructure towards great scalability and high efficiency, and provide flexible environment support for simulating various real-world scenarios, which enables parallel execution of multiple agents, centralized workflow orchestration, and both inter-agent and agent-environment interactions among agents. Moreover, we integrate an easy-to-use configurable tool and an automatic background generation pipeline in AgentScope, simplifying the process of creating agents with diverse yet detailed background settings. Last but not least, we provide a web-based interface for conveniently monitoring and managing a large number of agents that might deploy across multiple devices. We conduct a comprehensive simulation to demonstrate the effectiveness of the proposed enhancements in AgentScope, and provide detailed observations and discussions to highlight the great potential of applying multi-agent systems in large-scale simulations. The source code is released on GitHub at https://github.com/modelscope/agentscope to inspire further research and development in large-scale multi-agent simulations.