Think3D: Thinking with Space for Spatial Reasoning
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_ | 1866912970328506368 |
|---|---|
| author | Zhang, Zaibin Wu, Yuhan Jia, Lianjie Wang, Yifan Zhang, Zhongbo Li, Yijiang Ran, Binghao Zhang, Fuxi Sun, Zhuohan Yin, Zhenfei Wang, Lijun Lu, Huchuan |
| author_facet | Zhang, Zaibin Wu, Yuhan Jia, Lianjie Wang, Yifan Zhang, Zhongbo Li, Yijiang Ran, Binghao Zhang, Fuxi Sun, Zhuohan Yin, Zhenfei Wang, Lijun Lu, Huchuan |
| contents | While contemporary Vision-Language Models (VLMs) excel at 2D visual understanding, they remain constrained by a passive, 2D-centric paradigm that severely limits genuine 3D spatial reasoning. To bridge this gap, we introduce Think3D, a novel framework that equips VLM agents with interactive, 3D chain-of-thought reasoning capabilities. By integrating a suite of 3D manipulation tools, Think3D transforms passive perception into active spatial exploration, closely mirroring human geometric reasoning. We demonstrate that Think3D acts as a highly effective zero-shot plug-in for state-of-the-art closed-source models (e.g., GPT-4.1, Gemini 2.5 Pro), yielding absolute performance gains of +7.8% on BLINK Multi-view and MindCube, and +4.7% on VSI-Bench. Furthermore, to optimize tool-use in smaller open-weight models, we propose Think3D-RL, a reinforcement learning paradigm designed to autonomously learn spatial exploration strategies. When applied to Qwen3-VL-4B, Think3D-RL amplifies the performance gain from a marginal +0.7% to a substantial +10.7%. Notably, this RL formulation induces an exploration policy that qualitatively aligns with the sophisticated behavior of much larger models, entirely circumventing the need for costly operation-trajectory annotations. Ultimately, Think3D establishes tool-augmented active exploration as an effective paradigm for unlocking human-like 3D reasoning in multimodal agents. Code, models, and data are available at https://github.com/zhangzaibin/spagent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_13029 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Think3D: Thinking with Space for Spatial Reasoning Zhang, Zaibin Wu, Yuhan Jia, Lianjie Wang, Yifan Zhang, Zhongbo Li, Yijiang Ran, Binghao Zhang, Fuxi Sun, Zhuohan Yin, Zhenfei Wang, Lijun Lu, Huchuan Computer Vision and Pattern Recognition While contemporary Vision-Language Models (VLMs) excel at 2D visual understanding, they remain constrained by a passive, 2D-centric paradigm that severely limits genuine 3D spatial reasoning. To bridge this gap, we introduce Think3D, a novel framework that equips VLM agents with interactive, 3D chain-of-thought reasoning capabilities. By integrating a suite of 3D manipulation tools, Think3D transforms passive perception into active spatial exploration, closely mirroring human geometric reasoning. We demonstrate that Think3D acts as a highly effective zero-shot plug-in for state-of-the-art closed-source models (e.g., GPT-4.1, Gemini 2.5 Pro), yielding absolute performance gains of +7.8% on BLINK Multi-view and MindCube, and +4.7% on VSI-Bench. Furthermore, to optimize tool-use in smaller open-weight models, we propose Think3D-RL, a reinforcement learning paradigm designed to autonomously learn spatial exploration strategies. When applied to Qwen3-VL-4B, Think3D-RL amplifies the performance gain from a marginal +0.7% to a substantial +10.7%. Notably, this RL formulation induces an exploration policy that qualitatively aligns with the sophisticated behavior of much larger models, entirely circumventing the need for costly operation-trajectory annotations. Ultimately, Think3D establishes tool-augmented active exploration as an effective paradigm for unlocking human-like 3D reasoning in multimodal agents. Code, models, and data are available at https://github.com/zhangzaibin/spagent. |
| title | Think3D: Thinking with Space for Spatial Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.13029 |