构建融合物理与社交的异构多智能体环境，支持大模型模拟建筑使用者行为。
IndoorWorld: Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment
- 设计异构多智能体环境，同步建模物理任务与社会互动。
- 在办公室场景中验证协作、资源竞争与空间布局对行为的影响。
- 适合建筑智能化、人机交互与社会模拟研究者使用。
虚拟环境对人工智能代理研究至关重要。现有基于大语言模型（LLM）的代理研究环境通常侧重于物理任务求解或社会模拟，前者忽视个体差异与社会动态，后者缺乏社会行为的物理基础。我们提出 IndoorWorld，一个紧密整合物理与社会动态的异构多智能体环境。通过为 LLM 驱动的代理引入新挑战——即利用社会动态影响物理环境，并将社会互动锚定于世界状态，IndoorWorld 开启了基于大模型的建筑使用者模拟的可能性。我们在办公室场景中开展一系列实验，考察多智能体协作、资源竞争和空间布局对代理行为的影响。
原文摘要 · Abstract (English)
Virtual environments are essential to AI agent research. Existing environments for LLM agent research typically focus on either physical task solving or social simulation, with the former oversimplifying agent individuality and social dynamics, and the latter lacking physical grounding of social behaviors. We introduce IndoorWorld, a heterogeneous multi-agent environment that tightly integrates physical and social dynamics. By introducing novel challenges for LLM-driven agents in orchestrating social dynamics to influence physical environments and anchoring social interactions within world states, IndoorWorld opens up possibilities of LLM-based building occupant simulation for architectural design. We demonstrate the potential with a series of experiments within an office setting to examine the impact of multi-agent collaboration, resource competition, and spatial layout on agent behavior.
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。