# Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes

arXiv: https://arxiv.org/abs/2510.19400 · HTML: https://mlsanity.com/paper/2510.19400/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 50 of its 63 references that are in the map.
- First posted on arXiv 22 Oct 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, 30 of 50)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [BLINK: Multimodal Large Language Models Can See but Not Perceive](https://mlsanity.com/paper/2404.12390/) (2024)
- [InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models](https://mlsanity.com/paper/2404.07191/) (2024)
- [CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation](https://mlsanity.com/paper/2411.19650/) (2024)
- [AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems](https://mlsanity.com/paper/2503.06669/) (2025)
- [SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models](https://mlsanity.com/paper/2406.01584/) (2024)
- [Visual Spatial Reasoning](https://mlsanity.com/paper/2205.00363/) (2022)
- [MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details](https://mlsanity.com/paper/2507.02546/) (2025)
- [LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias](https://mlsanity.com/paper/2410.17242/) (2024)
- [MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence](https://mlsanity.com/paper/2505.23764/) (2025)
- [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024)
- [UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler](https://mlsanity.com/paper/2502.20110/) (2025)
- [VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction](https://mlsanity.com/paper/2505.20279/) (2025)
- [SpatialBot: Precise Spatial Understanding with Vision Language Models](https://mlsanity.com/paper/2406.13642/) (2024)

## Built on by (most cited first, 20 of 20)

- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [What Should I Cite? A RAG Benchmark for Academic Citation Prediction](https://mlsanity.com/paper/2601.14949/) (2026)
- [Diffusion Model as a Generalist Segmentation Learner](https://mlsanity.com/paper/2604.24575/) (2026)
- [OpenFrontier: General Navigation with Visual-Language Grounded Frontiers](https://mlsanity.com/paper/2603.05377/) (2026)
- [LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models](https://mlsanity.com/paper/2511.11334/) (2025)
- [MultiPress: A Multi-Agent Framework for Interpretable Multimodal News Classification](https://mlsanity.com/paper/2604.03586/) (2026)
- [SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding](https://mlsanity.com/paper/2606.22694/) (2026)
- [Learning Multi-View Spatial Reasoning from Cross-View Relations](https://mlsanity.com/paper/2603.27967/) (2026)
- [Consistent Yet Wrong: Evidence Insensitivity in Spatial Vision-Language Models](https://mlsanity.com/paper/2606.02742/) (2026)
- [Modality Fault Lines: Structural Corruptions Reveal Fragile Omni-Modal Reasoning](https://mlsanity.com/paper/2608.29278/) (2026)
- [RoboPIN: Grounded Embodied Reasoning via Pinned Chain-of-Thought](https://mlsanity.com/paper/2606.15753/) (2026)
- [EmbodimentSemantic: A Spatial Scene-Graph Dataset and Benchmark for Vision-Language Models on Embodied Manipulation Trajectories](https://mlsanity.com/paper/2607.00020/) (2026)
- [DINOcular: Self-Supervised Visuospatial Representations](https://mlsanity.com/paper/2608.27226/) (2026)
- [Di2CycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schr"odinger Bridge Transformer](https://mlsanity.com/paper/2608.29043/) (2026)
- [JPO: Juris Policy Optimization for Structured Legal Reasoning in Criminal Judgment Prediction](https://mlsanity.com/paper/2608.29616/) (2026)
- [SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem](https://mlsanity.com/paper/2609.07064/) (2026)
- [SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation](https://mlsanity.com/paper/2609.16601/) (2026)
- [Seeing Is Not Measuring: Tool-Augmented Metric Spatial Reasoning for Vision-Language Models](https://mlsanity.com/paper/2609.29073/) (2026)
- [SkillWeaver: Agentic Exploration over Neural Interaction Skills for Scalable Robot Data Generation](https://mlsanity.com/paper/2609.36171/) (2026)
- [Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence](https://mlsanity.com/paper/2610.20312/) (2026)

## Abstract (arXiv)

Vision-language models (VLMs) are essential to Embodied AI, enabling robots to perceive, reason, and act in complex environments. They also serve as the foundation for the recent Vision-Language-Action (VLA) models. Yet most evaluations of VLMs focus on single-view settings, leaving their ability to integrate multi-view information underexplored. At the same time, multi-camera setups are increasingly standard in robotic platforms, as they provide complementary perspectives to mitigate occlusion and depth ambiguity. Whether VLMs can effectively leverage such multi-view inputs for robotic reasoning therefore remains an open question. To bridge this gap, we introduce MV-RoboBench, a benchmark specifically designed to evaluate the multi-view spatial reasoning capabilities of VLMs in robotic manipulation. MV-RoboBench consists of 1.7k manually curated QA items across eight subtasks, divided into two primary categories: spatial understanding and robotic execution. We evaluate a diverse set of existing VLMs, including both open-source and closed-source models, along with enhanced versions incorporating CoT-inspired techniques. The results show that state-of-the-art models remain far below human performance, underscoring the substantial challenges VLMs face in multi-view robotic perception. Additionally, our analysis uncovers two key findings: (i) spatial intelligence and robotic task execution are positively correlated in multi-view robotic scenarios; and (ii) strong performance on existing general-purpose single-view spatial understanding benchmarks does not reliably translate to success in the robotic spatial tasks assessed by our benchmark. We release MV-RoboBench as an open resource to foster progress in spatially grounded VLMs and VLAs, providing not only data but also a standardized evaluation protocol for multi-view embodied reasoning.