Seeing Is Not Measuring: Tool-Augmented Metric Spatial Reasoning for Vision-Language Models

arXiv:2609.29073 · cs.CV · Submitted 2026-09-24 · Read on arXiv

cs.CV

Submitted: 2026-09-24

Updated: 2026-09-24

Terminology

• Accuracy — 18× in this paper · explained in 1 episode
• Grounding — 11× in this paper · explained in 3 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Trace — 6× in this paper · explained in 2 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Conference on Computer Vision and Pattern Recognition — 2× in this paper
• Core — 2× in this paper · explained in 2 episodes
• Mean Relative Accuracy — 2× in this paper
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Agentic Framework — 1× in this paper · explained in 6 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Error Decomposition — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Point Clouds — 1× in this paper · explained in 2 episodes
• Systematic Bias — 1× in this paper · explained in 3 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• WildDet3D: Scaling Promptable 3D Detection in the Wild
• SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
• MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence
• SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors
• ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models
• Toolformer: Language Models Can Teach Themselves to Use Tools
• VGGT: Visual Geometry Grounded Transformer
• Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
• SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards
• Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
• SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL
• Geometrically-Constrained Agent for Spatial Reasoning
• VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
• Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes
• Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces
• Visual Spatial Tuning
• Cambrian-S: Towards Spatial Supersensing in Video
• Open Vocabulary Monocular 3D Object Detection
• ReAct: Synergizing Reasoning and Acting in Language Models
• ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models