StateSight is a new benchmark designed to isolate and evaluate the ability of vision‑language models to reconstruct latent spatial structure from a single image. It consists of three procedurally generated task families—cube‑net opposite‑face reasoning, occluded cube‑tower counting, and 4‑neighbor connected‑component counting—each with 300 deterministic prompts and exact‑match scoring. The benchmark also includes a companion dataset, StateSight‑Steps, with 900 image‑text examples and 3,600 intermediate visual states to aid analysis of reconstruction errors.
arXiv:2607. 00491v1 Announce Type: cross Abstract: Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input.
arXiv:2607. 22864v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably.
arXiv:2606. 26535v1 Announce Type: cross Abstract: Current VLM evaluations often conflate language priors with genuine spatial reasoning.
The paper introduces PCSR-Bench, a benchmark of 84,373 question‑answer pairs derived from 2,600 omnidirectional images across 26 indoor environments, designed to evaluate perspective‑conditioned spatial reasoning (PCSR) in multimodal large language models (MLLMs). It reports a significant perception–reasoning gap, with accuracy dropping from 57.59% on limited field‑of‑view reasoning to as low as 0.64% on open‑ended compositional directional chains. An RL‑based diagnostic study on a 7B‑scale model shows that reward shaping can improve performance to 60.06% on a controlled task, indicating partial plasticity of PCSR capabilities.
Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnostic evaluation paradigm that assesses visual spatial intelligence through consistency, the alignment between implicit perception and explicit reasoning.
arXiv:2605.12413v4 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) show strong visual perception, yet remain limited in reasoning about space under changing viewpoints. We s...
arXiv:2609.16233v1 Announce Type: cross Abstract: Vision-language models excel at 2D image understanding but remain limited in 3D spatial reasoning. Progress is hindered by limitations in current ben...
The paper introduces GSM8K‑V, a new benchmark that converts the GSM8K grade‑school math word problems into multi‑image sequences while preserving semantic equivalence. It requires vision‑language models to extract quantities through visual perception and reconstruct reasoning chains by integrating implicit cues across scenes. Evaluation of 34 VLMs shows a large modality gap: most models score above 90 % on text, but the best reaches only 59 % on GSM8K‑V, highlighting a distinct challenge in implicit visual inference.
arXiv:2606. 16122v1 Announce Type: new Abstract: Visual thinking should not only sound right; it should show its evidence.
VBVR-Pro is a closed‑loop testbed that enables native visual reasoning through generation, offering 300 procedurally generated tasks that scale training and allow strong transfer to external benchmarks. It supplies verifiable reward scorers based on deterministic, task‑specific rules, outperforming VLM‑as‑a‑judge approaches and providing reliable signals for reinforcement learning. The suite also facilitates controlled modality studies, revealing that video generation excels at persistent spatiotemporal tracking while interleaved generation offers a compute‑efficient alternative, and highlights the importance of vision‑native trajectories for reasoning.
SpaceCast-Bench is a new benchmark that evaluates predictive spatial reasoning in vision‑language models, moving beyond simple spatial perception to tasks that require constructing scenes, anticipating interventions, and reasoning about unseen outcomes. It contains 3,862 questions from 182 real‑world scenes across 16 task types and three difficulty levels—static perception, local prediction, and global prediction—testing scene understanding, spatial state updating, and relational inference. Evaluation of 21 models shows a large performance gap, with the best model achieving only 58.0% versus 87.2% human accuracy, and fine‑tuning on the benchmark’s programmatically generated data can substantially improve model performance.
arXiv:2603. 25629v2 Announce Type: replace-cross Abstract: While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs).