# SpatialPrompting: Keyframe-driven Zero-Shot Spatial Reasoning with Off-the-Shelf Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2505.04911 · HTML: https://mlsanity.com/paper/2505.04911/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 15 of its 56 references that are in the map.
- First posted on arXiv 8 May 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 15 of 15)

- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos](https://mlsanity.com/paper/2405.19209/) (2024)
- [A Simple LLM Framework for Long-Range Video Question-Answering](https://mlsanity.com/paper/2312.17235/) (2023)
- [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024)
- [Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes](https://mlsanity.com/paper/2308.08769/) (2023)
- [Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search](https://mlsanity.com/paper/2303.06573/) (2023)
- [LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences](https://mlsanity.com/paper/2412.01292/) (2024)
- [Zero-Shot Video Question Answering with Procedural Programs](https://mlsanity.com/paper/2312.00937/) (2023)
- [VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs](https://mlsanity.com/paper/2409.20365/) (2024)
- [3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding](https://mlsanity.com/paper/2307.13363/) (2023)
- [Long Video Understanding with Learnable Retrieval in Video-Language Models](https://mlsanity.com/paper/2312.04931/) (2023)

## Built on by (most cited first, 7 of 7)

- [Think3D: Thinking with Space for Spatial Reasoning](https://mlsanity.com/paper/2601.13029/) (2026)
- [Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning](https://mlsanity.com/paper/2606.11683/) (2026)
- [OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping](https://mlsanity.com/paper/2607.00881/) (2026)
- [Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning](https://mlsanity.com/paper/2606.07436/) (2026)
- [Flame3D: Zero-shot Compositional Reasoning of 3D Scenes with Agentic Language Models](https://mlsanity.com/paper/2605.09218/) (2026)
- [SPATIOROUTE: Dynamic Prompt Routing for Zero-Shot Spatial Reasoning](https://mlsanity.com/paper/2605.18209/) (2026)
- [Agentic Collaborative Cognition for Zero-Shot 3D Understanding](https://mlsanity.com/paper/2606.24649/) (2026)

## Abstract (arXiv)

This study introduces SpatialPrompting, a novel framework that harnesses the emergent reasoning capabilities of off-the-shelf multimodal large language models to achieve zero-shot spatial reasoning in three-dimensional (3D) environments. Unlike existing methods that rely on expensive 3D-specific fine-tuning with specialized 3D inputs such as point clouds or voxel-based features, SpatialPrompting employs a keyframe-driven prompt generation strategy. This framework uses metrics such as vision-language similarity, Mahalanobis distance, field of view, and image sharpness to select a diverse and informative set of keyframes from image sequences and then integrates them with corresponding camera pose data to effectively abstract spatial relationships and infer complex 3D structures. The proposed framework not only establishes a new paradigm for flexible spatial reasoning that utilizes intuitive visual and positional cues but also achieves state-of-the-art zero-shot performance on benchmark datasets, such as ScanQA and SQA3D, across several metrics. The proposed method effectively eliminates the need for specialized 3D inputs and fine-tuning, offering a simpler and more scalable alternative to conventional approaches.