# A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science

arXiv: https://arxiv.org/abs/2504.09848 · HTML: https://mlsanity.com/paper/2504.09848/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 60 of its 89 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 60)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [VIMA: General Robot Manipulation with Multimodal Prompts](https://mlsanity.com/paper/2210.03094/) (2022)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [Skillful Precipitation Nowcasting using Deep Generative Models of Radar](https://mlsanity.com/paper/2104.00954/) (2021)
- [NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models](https://mlsanity.com/paper/2305.16986/) (2023)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [FuXi: A cascade machine learning forecasting system for 15-day global weather forecast](https://mlsanity.com/paper/2306.12873/) (2023)
- [Factuality Enhanced Language Models for Open-Ended Text Generation](https://mlsanity.com/paper/2206.04624/) (2022)
- [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [Embodied Intelligence via Learning and Evolution](https://mlsanity.com/paper/2102.02202/) (2021)
- [SpatialBot: Precise Spatial Understanding with Vision Language Models](https://mlsanity.com/paper/2406.13642/) (2024)
- [EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI](https://mlsanity.com/paper/2312.16170/) (2023)
- [Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding](https://mlsanity.com/paper/2412.00493/) (2024)
- [GeomVerse: A Systematic Evaluation of Large Models for Geometric Reasoning](https://mlsanity.com/paper/2312.12241/) (2023)
- [Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation](https://mlsanity.com/paper/2402.14744/) (2024)
- [NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models](https://mlsanity.com/paper/2407.12366/) (2024)
- [Large Language Models are Geographically Biased](https://mlsanity.com/paper/2402.02680/) (2024)
- [Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping](https://mlsanity.com/paper/2402.14083/) (2024)
- [UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web](https://mlsanity.com/paper/2310.18340/) (2023)
- [Evaluating Cognitive Maps and Planning in Large Language Models with CogEval](https://mlsanity.com/paper/2309.15129/) (2023)
- [3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning](https://mlsanity.com/paper/2411.17735/) (2024)
- [VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View](https://mlsanity.com/paper/2307.06082/) (2023)
- [MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception](https://mlsanity.com/paper/2312.07472/) (2023)

## Built on by (most cited first, 12 of 12)

- [Think3D: Thinking with Space for Spatial Reasoning](https://mlsanity.com/paper/2601.13029/) (2026)
- [UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding](https://mlsanity.com/paper/2506.23219/) (2025)
- [Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluation](https://mlsanity.com/paper/2602.11635/) (2026)
- [Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence](https://mlsanity.com/paper/2603.07660/) (2026)
- [VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models](https://mlsanity.com/paper/2505.08455/) (2025)
- [Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System](https://mlsanity.com/paper/2506.19433/) (2025)
- [MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation](https://mlsanity.com/paper/2602.07082/) (2026)
- [GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language Models](https://mlsanity.com/paper/2510.07791/) (2025)
- [How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study](https://mlsanity.com/paper/2604.15294/) (2026)
- [Towards Camera-Robust 3D Localization: Equation-Anchored Tool-Use for MLLMs](https://mlsanity.com/paper/2605.19528/) (2026)
- [How Far Are Large Multimodal Models from Human-Level Spatial Action? A Benchmark for Goal-Oriented Embodied Navigation in Urban Airspace](https://mlsanity.com/paper/2604.07973/) (2026)
- [Towards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2610.19108/) (2026)

## Abstract (arXiv)

Over the past year, the development of large language models (LLMs) has brought spatial intelligence into focus, with much attention on vision-based embodied intelligence. However, spatial intelligence spans a broader range of disciplines and scales, from navigation and urban planning to remote sensing and earth science. What are the differences and connections between spatial intelligence across these fields? In this paper, we first review human spatial cognition and its implications for spatial intelligence in LLMs. We then examine spatial memory, knowledge representations, and abstract reasoning in LLMs, highlighting their roles and connections. Finally, we analyze spatial intelligence across scales -- from embodied to urban and global levels -- following a framework that progresses from spatial memory and understanding to spatial reasoning and intelligence. Through this survey, we aim to provide insights into interdisciplinary spatial intelligence research and inspire future studies.