R4：面向视觉语言模型在 4D 时空空间中的检索增强推理
R4: Retrieval-Augmented Reasoning for Vision-Language Models in 4D Spatio-Temporal Space
把物体级语义描述锚定到度量空间与时间轴上构建可跨智能体共享的 4D 知识库，并用语义/空间/时序三路键做检索，为 VLM 在具身场景中提供免训练的长时记忆与时空推理能力，可直接迁移到导航与情景问答。
原文依据 retrieval in R4 operates directly in structured 4D space, enabling episodic and collaborative reasoning without training
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论人类通过构建持久、结构化的内部表征来感知和推理周围环境，这些表征编码了语义含义、空间布局与时序动态，从而在四个维度（三个空间轴与一个时间轴）上完成认知。这种多模态记忆使人能够回忆过去事件、推断未观测状态，并将新信息整合进依赖上下文的推理之中。受此能力启发，我们提出 R4，一个在 4D 时空空间中进行检索增强推理的免训练框架，为视觉语言模型（VLM）赋予结构化、终身性的记忆。R4 通过将物体级语义描述锚定在度量空间与时间中，持续构建 4D 知识数据库，形成一个可在多个智能体之间共享的持久世界模型。在推理阶段，自然语言查询被分解为语义、空间与时序三类键以检索相关观测，并通过迭代式的检索—推理循环将其整合进 VLM 的推理过程。与经典检索增强生成方法不同，R4 的检索直接在结构化 4D 空间中运行，无需训练即可实现情景式与协作式推理。在具身问答与导航基准上的实验表明，相较于基线，R4 显著提升了对时空信息的检索与推理能力，推动了动态环境中具身 4D 推理的新范式。
英文原文摘要 1463 字符
Humans perceive and reason about their surroundings in four dimensions - three spatial and one temporal axis - by building persistent, structured internal representations that encode semantic meaning, spatial layout, and temporal dynamics. These multimodal memories enable them to recall past events, infer unobserved states, and integrate new information into context-dependent reasoning. Inspired by this capability, we introduce R4, a training-free framework for retrieval-augmented reasoning in 4D spatio-temporal space that equips vision-language models (VLMs) with structured, lifelong memory. R4 continuously constructs a 4D knowledge database by anchoring object-level semantic descriptions in metric space and time, yielding a persistent world model that can be shared across agents. At inference, natural language queries are decomposed into semantic, spatial, and temporal keys to retrieve relevant observations, which are integrated into the VLM's reasoning through an iterative retrieval-reasoning loop. Unlike classical retrieval-augmented generation methods, retrieval in R4 operates directly in structured 4D space, enabling episodic and collaborative reasoning without training. Experiments on embodied question answering and navigation benchmarks demonstrate that R4 substantially improves retrieval and reasoning over spatio-temporal information compared to baselines, advancing a new paradigm for embodied 4D reasoning in dynamic environments.