Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
By: Guanting Dong, Junting Lu, Junjie Huang, Wanjun Zhong, Longxiang Liu, Shijue Huang, Zhenyu Li, Yang Zhao, Xiaoshuai Song, Xiaoxi Li, Jiajie Jin, Yutao Zhu, Hanbin Wang, Fangyu Lei, Qinyu Luo, Mingyang Chen, Zehui Chen, Jiazhan
Published: 2026-04-21
View on arXiv →#cs.AI
Abstract
This paper introduces Agent-World, a framework for scaling real-world environment synthesis to facilitate the evolution of general agent intelligence. It explores methodologies for creating complex, realistic simulations that enable AI agents to learn and adapt to diverse scenarios, crucial for applications in robotics, autonomous systems, and broader AI development.