Very Large-Scale Multi-Agent Simulation in AgentScope
Xuchen Pan Alibaba Group Dawei Gao Alibaba Group Yuexiang Xie Alibaba Group Yushuo Chen Alibaba Group Zhewei Wei Renmin University of China Yaliang Li Alibaba Group Bolin Ding Alibaba Group Ji-Rong Wen Renmin University of China Jingren Zhou Alibaba Group
Abstract
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, automatic workflow conversion for distributed deployment, and both inter-agent and agent-environment interactions. 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 backgroun
中文速览
大规模多智能体仿真长期面临三大瓶颈：系统扩展性差、智能体同质化严重、以及管理成本高昂。研究团队在已有的AgentScope平台基础上，引入了基于Actor模型的分布式并行机制——让互不依赖的智能体同时运行，并支持一行代码完成从单机到分布式的迁移；同时设计了可配置的人口分布工具和自动背景生成流水线，让百万量级的智能体在年龄、职业、教育等维度上呈现真实多样的差异；还提供了可视化的Agent-Manager界面，方便跨设备监控和管理海量智能体。以经典的"猜均值三分之二"博弈游戏为验证场景，仅用4台设备便成功运行了100万智能体的仿真，结果表明该平台在运行效率和智能体行为多样性上均有显著提升，为社会科学、经济学等领域开展超大规模LLM驱动仿真研究提供了切实可行的基础设施。
原文 arXiv:2407.17789;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2407.17789v2