As a cornerstone of the modern digital economy, 3D modeling and rendering demand substantial resources and manual effort when scene editing is performed in the traditional manner. Despite recent progress in VLM-based agents for 3D editing, the fundamental trade-off between editing precision and agent responsiveness remains unresolved. To overcome these limitations, we present EZBlender, a Blender agent with a hybrid framework that combines planning-based task decomposition and reactive local autonomy for efficient human AI collaboration and semantically faithful 3D editing. Specifically, this unexplored Plan-and-ReAct design not only preserves editing quality but also significantly reduces latency and computational cost. To further validate the efficiency and effectiveness of the proposed edge-autonomy architecture, we construct a dedicated multi-tasking benchmark that has not been systematically investigated in prior research. In addition, we provide a comprehensive analysis of language model preference, system responsiveness, and economic efficiency.
@article{arxiv.2601.07143,
title = {EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent},
author = {Hao Wang and Wenhui Zhu and Shao Tang and Zhipeng Wang and Xuanzhao Dong and Xin Li and Xiwen Chen and Ashish Bastola and Xinhao Huang and Yalin Wang and Abolfazl Razi},
journal= {arXiv preprint arXiv:2601.07143},
year = {2026}
}