MAAIJun 14, 2025

IndoorWorld: Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment

arXiv:2506.12331v11 citationsh-index: 13EMNLP
Originality Incremental advance
AI Analysis

This addresses the need for more realistic AI agent environments for applications like architectural design, though it appears incremental as it combines existing elements rather than introducing a fundamentally new approach.

The paper tackles the problem of existing virtual environments for LLM agents being limited to either physical task solving or social simulation, by introducing IndoorWorld, a heterogeneous multi-agent environment that integrates both, enabling experiments on collaboration, competition, and spatial layout in an office setting.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes