Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests

• URL: http://arxiv.org/abs/2607.22864v1
• Date: Fri, 24 Jul 2026 19:09:25 GMT
• Title: Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests
• Abstract summary: Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably.<n>We introduce Spatial-IQ, a hierarchical diagnostic framework that decomposes object counting in stacked 3D structures into 9 perceptual and cognitive sub-tasks.<n>We evaluate models across three output formats (free-response text, multiple-choice images, and image editing) alongside a human baseline.
• Score: 8.148716256952607
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably. Existing benchmarks evaluate these models as black boxes, limiting their ability to identify the underlying causes of lower performance: when a model fails a spatial reasoning task, it remains difficult to ascertain whether the hurdle is perceptual, such as recognizing object boundaries, or cognitive, such as reasoning about occlusion to infer hidden geometry. We introduce Spatial-IQ, a hierarchical diagnostic framework that decomposes object counting in stacked 3D structures into 9 perceptual and cognitive sub-tasks organized by the developmental stages of human spatial cognition, with mental rotation as an additional target probe. Using NVIDIA Isaac Sim, we procedurally generated a diverse dataset of roughly 80,000 stacked 3D structures with per-task ground truth. We evaluate models across three output formats (free-response text, multiple-choice images, and image editing) alongside a human baseline. The Spatial-IQ framework shows that top-performing models often succeed at the target task (object counting) without succeeding on the lower-level sub-tasks intended to support it, and that models differ in how much of these hierarchical chains they preserve, often revealing shortcut behavior that raw target-task accuracy alone would obscure. Finally, we demonstrate that training models with chain-of-thought (CoT) supervision over our hierarchical sub-tasks, combined with reinforcement learning with verifiable rewards, significantly improves both spatial consistency across sub-tasks and target-task accuracy, supporting the value of the proposed decomposition as both a diagnostic tool and a training signal.

Related papers

• Promptable Concept Segmentation from Above: Evaluating SAM 3's Zero-Shot and One-Shot Capabilities in Remote Sensing [0.42970700836450487]
  We present a comprehensive, multi-task empirical evaluation across remote sensing scene classification, object detection, and instance segmentation.<n>Our results demonstrate that SAM 3 avoids the overfitting commonly seen in legacy domain-adapted models.<n>It remains fundamentally constrained by sub-pixel resolution limits and overhead semantic blind spots.
  arXiv  Detail & Related papers  (2026-07-10T16:33:05Z)
• Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models [50.6415287154632]
  Embodied3DBench is a robot-centric benchmark targeting low-level spatial intelligence in 3D environments.<n>The benchmark spans 12 subcategories and contains over 21k high-quality question-answer pairs.
  arXiv  Detail & Related papers  (2026-05-27T20:28:56Z)
• Beyond Shortcuts: Mitigating Visual Illusions in Frozen VLMs via Qualitative Reasoning [14.700305370711973]
  We propose a training-free, data-centric framework designed to fortify visual grounding in frozen Vision-Language Models.<n>Our framework was evaluated on the DataCV 2026 Challenge (Task I: Classic Illusion Understanding), where it ranked 2nd place overall.<n>Our success underscores the potential of structured qualitative grounding as a robust paradigm for developing next-generation, illusion-resistant vision-language systems.
  arXiv  Detail & Related papers  (2026-04-29T03:12:29Z)
• SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning [67.67774742200626]
  spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, is a core challenge for large language models.<n>We propose a unified multimodal generation framework that integrates textual reasoning with visual imagination.<n>Our framework adopts a divide-and-conquer strategy, using text chain-of-thought for high-level semantic planning and the visual imagination for geometry-sensitive state transformation and consistency preservation.
  arXiv  Detail & Related papers  (2026-04-19T11:21:59Z)
• EgoReasoner: Learning Egocentric 4D Reasoning via Task-Adaptive Structured Thinking [34.29831801830779]
  EgoReasoner is a framework that aligns the reasoning scaffold and the reward signal to each task's cognitive structure.<n>Our model achieves 37.5% average accuracy on the challenging HD-EPIC benchmark, surpassing Qwen2.5-VL-7B by over 10 points.
  arXiv  Detail & Related papers  (2026-03-06T18:49:04Z)
• Revisiting Multi-Task Visual Representation Learning [52.93947931352643]
  We introduce MTV, a principled multi-task visual pretraining framework.<n>We leverage high-capacity "expert" models to synthesize dense, structured pseudo-labels at scale.<n>Our results demonstrate that MTV achieves "best-of-both-worlds" performance.
  arXiv  Detail & Related papers  (2026-01-20T11:59:19Z)
• Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods [11.53401872925025]
  We argue that spatial ability is not solely determined by the input format.<n>Our survey introduces a taxonomy that organizes spatial intelligence from cognitive aspect.<n>We analyze methods for improving spatial ability, spanning both training-based and reasoning-based approaches.
  arXiv  Detail & Related papers  (2025-11-14T02:43:17Z)
• How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective [103.44502230776352]
  We present a systematic investigation of Visual Spatial Reasoning (VSR) in Vision-Language Models (VLMs)<n>We categorize spatial intelligence into three levels of capability, ie, basic perception, spatial understanding, spatial planning, and curate SIBench, a spatial intelligence benchmark encompassing nearly 20 open-source datasets across 23 task settings.
  arXiv  Detail & Related papers  (2025-09-23T12:00:14Z)
• PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly [77.33429729761596]
  We introduce PhyBlock, a progressive benchmark to assess vision-language models (VLMs) on physical understanding and planning.<n>PhyBlock integrates a novel four-level cognitive hierarchy assembly task alongside targeted Visual Question Answering (VQA) samples.<n>We benchmark 21 state-of-the-art VLMs, highlighting their strengths and limitations in physically grounded, multi-step planning.
  arXiv  Detail & Related papers  (2025-06-10T11:46:06Z)
• SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation [7.659514491338669]
  Current vision-language models may grasp basic spatial cues but struggle with the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications.<n>We develop SPHERE, a hierarchical evaluation framework supported by a new human-annotated dataset.<n> Benchmark evaluation of state-of-the-art models reveals significant deficiencies, especially in reasoning about distance and proximity.
  arXiv  Detail & Related papers  (2024-12-17T09:10:55Z)
• Multi-task Learning with 3D-Aware Regularization [55.97507478913053]
  We propose a structured 3D-aware regularizer which interfaces multiple tasks through the projection of features extracted from an image encoder to a shared 3D feature space. We show that the proposed method is architecture agnostic and can be plugged into various prior multi-task backbones to improve their performance.
  arXiv  Detail & Related papers  (2023-10-02T08:49:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.