EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912817550983168 |
|---|---|
| author | Wang, Hao Zhu, Wenhui Tang, Shao Wang, Zhipeng Dong, Xuanzhao Li, Xin Chen, Xiwen Bastola, Ashish Huang, Xinhao Wang, Yalin Razi, Abolfazl |
| author_facet | Wang, Hao Zhu, Wenhui Tang, Shao Wang, Zhipeng Dong, Xuanzhao Li, Xin Chen, Xiwen Bastola, Ashish Huang, Xinhao Wang, Yalin Razi, Abolfazl |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07143 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent Wang, Hao Zhu, Wenhui Tang, Shao Wang, Zhipeng Dong, Xuanzhao Li, Xin Chen, Xiwen Bastola, Ashish Huang, Xinhao Wang, Yalin Razi, Abolfazl Human-Computer Interaction 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. |
| title | EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2601.07143 |