摘要：多模态大语言模型（MLLM）已被广泛应用于具身智能体和机器人领域的视觉任务。然而，MLLM 在空间推理和感知方面仍存在局限。后训练技术已展现出提升这些能力的潜力，但针对这类方法的数据驱动型综述仍较为有限。本综述考察了针对空间推理任务对预训练 MLLM 进行微调的方法，涵盖从监督学习到强化学习的不同路径，并重点关注所使用的数据集。我们研究了数据集构建、数据模态与标注，以及最终模型评估等主题。基于这些主题，我们将相关研究划分为三类：数据集设计、数据集构建和评估。我们发现，构建固定空间标注主要有四种方法：规则与模板、LLM 提示、程序化生成，以及人类参与闭环（human-in-the-loop）。我们还观察到评估方法存在显著差异，包括不同的评分方法、容差指标和基准类型。最后，我们识别出未来研究的机会方向，包括统一动态标注、高效空间推理、评估标准化、扩展空间范围，以及以人为中心的空间交互。

Abstract:Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limitations in spatial reasoning and perception. Post-training techniques have shown promise for improving these capabilities; yet, there are limited data-driven surveys of such approaches. In this survey, we consider approaches to fine-tuning pretrained MLLMs for spatial reasoning tasks, ranging from supervised to reinforcement learning, with an emphasis on the datasets used. We investigate themes of dataset construction, data modality and annotation, and evaluation of the resulting models. Based on these themes, we categorize research into three groups: dataset design, dataset construction and evaluation. We find four main methods for constructing fixed spatial annotations: rules and templates, LLM prompting, procedural generation, and human-in-the-loop. We also observe substantial variation in evaluation approaches, including different scoring methods, tolerance metrics, and benchmark types. Finally, we identify opportunities for future research in unified dynamic annotation, efficient spatial reasoning, standardization of evaluation, expanded spatial range, and human-centered spatial interactions.