两个轻量级仿真框架，让普通电脑也能运行大模型驱动的2D/3D智能体。
Minimal Local Simulation Foundations for LLM- and VLM-Driven Agents in 2D and 3D Environments
- 基于本地部署的LLM/VLM，实现2D/3D环境中智能体自主移动与交互
- 支持空间事件如火灾触发响应，2D环境可模拟多智能体行为
- 开源可修改，适合教学、快速原型开发和领域定制扩展
大型语言模型（LLMs）和视觉语言模型（VLMs）正在拓展基于智能体仿真的行为表达范围，但当前多数平台难以研究、修改或在普通计算机上运行。本文提出两个刻意简化的设计方案：SD-AgentFoundry-2D 提供二维多智能体环境，本地部署的 LLM 智能体可移动、通信、响应位置占用，并遭遇局部空间火灾事件；SD-AgentFoundry-3D 提供三维数字孪生环境，本地部署的 VLM 接收第一人称图像并生成自然语言移动指令。两个代码库均支持 macOS、Windows、Linux 本地运行，设计为可自由修改而非成品应用。两者共同提供学习生成式社会仿真及构建领域特定扩展的入门起点。
原文摘要 · Abstract (English)
Large language models (LLMs) and vision-language models (VLMs) are expanding the range of behaviors that can be represented in agent-based simulations, but many contemporary platforms are difficult to study, modify, or run on ordinary computers. We present two intentionally minimal simulation foundations for education and rapid prototyping. SD-AgentFoundry-2D provides a two-dimensional multi-agent environment in which locally hosted LLM agents move, communicate, respond to place occupancy, and encounter spatially localized fire events. SD-AgentFoundry-3D provides a three-dimensional digital-twin environment in which a locally hosted VLM receives first-person images and produces natural-language movement instructions. Both codebases are designed to run locally on macOS, Windows, and Linux and are deliberately left open to modification rather than developed as finished applications. Together, they offer accessible starting points for learning about generative social simulation and for building domain-specific extensions.
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。