Can VLMs predict how each camera move changes the view, and plan many such moves ahead? We call this capability view planning, requiring (1)understanding how a single action transforms the view, and (2)composing many such transformations across multi-turn plans to identify a target view. We probe both abilities in our proposed ViewSuite, a 3D point-cloud environment on real ScanNet scenes. Across 13 frontier VLMs, a critical planning gap emerges: they possess basic view-action knowledge but fail to compose it across multi-turn plans, with the gap widening as viewpoint distance grows. To close this gap, we propose an iterative framework that alternates self-exploration with view graph distillation. The key insight is that all exploration trajectories, regardless of their outcome, collectively form a view graph that compactly captures how viewpoints connect across a scene. Distilling this graph into diverse supervised tasks reshapes the policy distribution and overcomes the sparse rewards that stall pure RL. This improves Qwen2.5-VL-7B from 2.5% to 47.8% on interactive view planning, surpassing GPT-5.4 Pro (18.5%) and Gemini 3.1 Pro (21.4%). Self-exploration emerges as a promising path toward VLMs that can actively reason and plan in 3D space. Code and Data are at https://viewsuite.github.io.

翻译：视觉语言模型能否预测每次相机移动如何改变视角，并提前规划多次移动？我们将这种能力称为视角规划，这需要(1)理解单个动作如何改变视角，以及(2)在多次规划中组合这些变换以识别目标视角。我们在提出的ViewSuite中探究了这两种能力，这是一个基于真实ScanNet场景的3D点云环境。在对13个前沿视觉语言模型的评估中，出现了一个关键的规划鸿沟：它们具备基本的视角-动作知识，但无法在多步规划中组合这些知识，且随着视角距离增大，这一差距会扩大。为弥合这一差距，我们提出了一种迭代框架，该框架交替进行自探索与视角图蒸馏。关键洞察在于：所有探索轨迹，无论其结果如何，共同构成了一张视角图，该图紧凑地捕捉了场景中视角之间的连接关系。将此图蒸馏到多样化监督任务中，可以重塑策略分布，并克服纯强化学习中的稀疏奖励问题。这使得Qwen2.5-VL-7B在交互式视角规划上的性能从2.5%提升至47.8%，超过了GPT-5.4 Pro（18.5%）和Gemini 3.1 Pro（21.4%）。自探索为视觉语言模型在3D空间中主动推理与规划提供了一条有前景的路径。代码与数据见https://viewsuite.github.io。