空间推理一直是视觉语言模型的硬伤，SCOUT 用新的训练方法把 3D 理解做得更准，7B 规模直接超过 GPT-4o，还能迁移到视频上。
SCOUT 提出结构化思维链框架，显式建模 3D 环境感知以增强空间理解。其强化学习算法引入多目标过程奖励和定制的优势估计方法，实现推理轨迹的细粒度信用分配。研究者构建了 SCOUT-24k 结构化空间推理数据集。SCOUT-3B 在通用空间基准上提升 16.85%，在复杂空间推理任务上提升 6.3%。SCOUT-7B 超出 GPT-4o 4.28%，且能泛化到多图像和视频场景。
SCOUT: Unlocking Enhanced Spatial Reasoning via Structured Chain-of-Thought and Multi-Objective Process Reward
Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to close this gap with verifiable outcomes, yet they suffer from poor credit assignment across intermediate reasoning steps. Concurrently, structured reasoning approaches overlook the critical depth perception necessary for comprehensive 3D understanding. To address these challenges, we propose SCOUT (Structured Chain-Of-Thought Utilizing Process-Supervised RL Training). Specifically, we design a structured Chain-of-Thought (CoT) framework that explicitly models 3D environmental perception to ensure robust spatial understanding and reasoning. Furthermore, we introduce a novel RL algorithm featuring multi-objective process rewards and a tailored advantage estimation method, facilitating fine-grained credit assignment across distinct segments of the reasoning trajectory. To support our framework, we develop SCOUT-24k, a structured spatial reasoning CoT dataset synthesized through a customized pipeline. Extensive evaluations demonstrate that SCOUT-3B improves upon baseline models by 16.85% and 6.3% on general spatial benchmarks and complex spatial reasoning tasks respectively. Notably, our larger SCOUT-7B even outperforms GPT-4o by a margin of 4.28%. Moreover, despite being trained exclusively on single image, SCOUT-7B exhibits robust out-of-domain generalization to multi-image and video scenarios. These empirical results render SCOUT as a critical step towards next generation of spatially-aware VLMs.