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

近年來大型語言模型（LLMs）的最新進展為在非常大規模模擬中應用多智能體系統開辟了新的途徑。然而，在使用現有平台進行多智能體模擬時仍存在一些挑戰，如可擴展性有限、效率低下、智能體多樣性不足以及管理過程耗時。為應對這些挑戰，我們為AgentScope開發了多項新功能和組件，進一步提升其便利性和靈活性，以支持非常大規模的多智能體模擬。具體而言，我們提出了一個基於演員的分佈式機制作為底層技術基礎，以實現極高的可擴展性和效率，並為模擬各種現實場景提供靈活的環境支持，實現多智能體的並行執行、中央化工作流程編排，以及智能體之間的互動以及智能體與環境之間的互動。此外，我們在AgentScope中整合了一個易於配置的工具和自動背景生成流水線，簡化了創建具有多樣性且詳細背景設置的智能體的過程。最後，我們提供了一個基於Web的界面，方便監控和管理可能部署在多個設備上的大量智能體。我們進行了全面的模擬，以展示在AgentScope中提出的增強功能的有效性，並提供詳細的觀察和討論，以突顯在大規模模擬中應用多智能體系統的巨大潛力。源代碼已在GitHub上釋出，網址為https://github.com/modelscope/agentscope，以激發大規模多智能體模擬領域的進一步研究和發展。

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.