通过乱序执行提升大模型多智能体仿真效率，显著减少等待时间。
AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution
- 动态追踪智能体真实依赖关系，减少虚假依赖
- 相比传统同步模拟，速度提升1.3倍至4.15倍
- 适合大规模社会模拟与游戏场景的高效建模
随着大型语言模型（LLM）在自然语言理解与推理能力上的进步，基于LLM的智能体被越来越多地用于模拟环境中完成复杂任务、与其他智能体交互，并展现出与社会科学和游戏相关的涌现行为。然而，当前多智能体仿真常因虚假依赖导致并行性受限，造成性能瓶颈。本文提出AI Metropolis，一种采用乱序执行调度的仿真引擎，通过动态追踪智能体间的实际依赖关系，最小化虚假依赖，提升并行度并实现高效的硬件利用。评估表明，相较于采用全局同步的标准并行模拟，AI Metropolis在智能体数量增加时接近最优性能，速度提升达1.3倍至4.15倍。
原文摘要 · Abstract (English)
With more advanced natural language understanding and reasoning capabilities, large language model (LLM)-powered agents are increasingly developed in simulated environments to perform complex tasks, interact with other agents, and exhibit emergent behaviors relevant to social science and gaming. However, current multi-agent simulations frequently suffer from inefficiencies due to the limited parallelism caused by false dependencies, resulting in performance bottlenecks. In this paper, we introduce AI Metropolis, a simulation engine that improves the efficiency of LLM agent simulations by incorporating out-of-order execution scheduling. By dynamically tracking real dependencies between agents, AI Metropolis minimizes false dependencies, enhancing parallelism and enabling efficient hardware utilization. Our evaluations demonstrate that AI Metropolis achieves speedups from 1.3x to 4.15x over standard parallel simulation with global synchronization, approaching optimal performance as the number of agents increases.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。