Existing Multimodal Large Language Models (MLLMs) struggle with 3D spatial reasoning, as they fail to construct structured abstractions of the 3D environment depicted in video inputs. To bridge this gap, drawing inspiration from cognitive theories of allocentric spatial reasoning, we investigate how to enable MLLMs to model and reason over text-based spatial representations of video. Specifically, we introduce Textual Representation of Allocentric Context from Egocentric Video (TRACE), a prompting method that induces MLLMs to generate text-based representations of 3D environments as intermediate reasoning traces for more accurate spatial question answering. TRACE encodes meta-context, camera trajectories, and detailed object entities to support structured spatial reasoning over egocentric videos. Extensive experiments on VSI-Bench and OST-Bench demonstrate that TRACE yields notable and consistent improvements over prior prompting strategies across a diverse range of MLLM backbones, spanning different parameter scales and training schemas. We further present ablation studies to validate our design choices, along with detailed analyses that probe the bottlenecks of 3D spatial reasoning in MLLMs.

翻译：现有的大语言模型（MLLMs）在处理3D空间推理时表现不佳，因为它们无法对视频输入中描绘的3D环境构建结构化抽象。为弥补这一差距，我们借鉴异我中心空间推理的认知理论，探索如何使MLLMs能够建模并推理基于文本的视频空间表征。具体而言，我们提出了“从自我中心视频到异我中心上下文的文本表征”（TRACE），这是一种提示方法，通过诱导MLLMs生成3D环境的文本表征作为中间推理轨迹，从而实现更准确的空间问答。TRACE编码了元上下文、相机轨迹和详细的对象实体，以支持基于自我中心视频的结构化空间推理。在VSI-Bench和OST-Bench上的大量实验表明，与先前的提示策略相比，TRACE在多种MLLM骨干网络上（涵盖不同参数规模与训练范式）均取得了显著且一致的改进。我们进一步通过消融实验验证了设计选择的有效性，并展开了详细分析，探讨了MLLMs在3D空间推理中的瓶颈所在。