SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds

Xiaokang Ye, Jiawei Ren, Yan Zhuang, Xuhong He, Yiming Liang, Yiqing Yang, Mrinaal Dogra, Xianrui Zhong, Eric Liu, Kevin Benavente, Rajiv Mandya Nagaraju, Dhruv Vivek Sharma, Ziqiao Ma, Tianmin Shu, Zhiting Hu, Lianhui Qin

Keywords: Multi-Agent Simulator, Real World Agent, Social Simulation, Physical Simulation

Abstract: While LLM/VLM-powered AI agents have advanced rapidly in math, coding, and computer use, their applications in complex physical and social environments remain challenging. Building agents that can survive and thrive in the real world (e.g., by autonomously earning income) requires massive-scale interaction, reasoning, training, and evaluation across diverse scenarios. However, existing world simulators for such development fall short: they often rely on limited hand-crafted environments, simulate simplified game-like physics and social rules, and lack native support for LLM/VLM agents. We introduce SimWorld, a new simulator built on Unreal Engine 5, designed for developing and evaluating LLM/VLM agents in rich, real-world-like settings. SimWorld offers three core capabilities: (1) realistic, open-ended world simulation, including accurate physical and social dynamics and language-driven procedural environment generation; (2) rich interface for LLM/VLM agents, with multi-modal world inputs/feedback and open-vocabulary action outputs at varying levels of abstraction; and (3) diverse physical and social reasoning scenarios that are easily customizable by users. We demonstrate SimWorld by deploying frontier LLM agents (e.g., Gemini-2.5-Flash, Claude-3.5, GPT-4o, and DeepSeek-Prover-V2) on both short-horizon navigation tasks requiring grounded re-planning, and long-horizon multi-agent food delivery tasks involving strategic cooperation and competition. The results reveal distinct reasoning patterns and limitations across models. We open-source SimWorld and hope it becomes a foundational platform for advancing real-world agent intelligence across disciplines. Please refer to the project website for the most up-to-date information: http://simworld.org/.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 18359