arXiv Computer Vision October 5, 2026 By Jinchang Zhang, Guoyu Lu

Seeing, Saying, but Not Using: From Reportable Spatial Facts to Usable States in Multimodal Large Language Models

Read the original on arXiv Computer Vision →

The paper introduces “SpaceConflict”, a benchmark of 23,196 multimodal inputs designed to test whether large language models can not only report spatial facts but also use them in reasoning. Experiments show a gap between a model’s ability to recover an initial spatial state from visual evidence and its ability to apply that state to perform transformations, with the gap narrowing but not closing as model size increases. To address this, the authors propose Operational State Supervision (OSS), which supervises task‑relevant spatial states and their transformation trajectories, improving accuracy on judgments that require state organization and use.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computation and Language

Sep 1

Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning

arXiv:2606.01914v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) remain unreliable on spatial multiple-choice questions, and their failures are often attributed to poorly...

By Chuang Ma, Qianying Liu, Tomoyuki Obuchi, Fei Cheng, Wang Yang, Sudong Cai, Shuyuan Zheng, Akiko Aizawa, Sadao Kurohashi

llms reinforcement-learning multimodal safety

arXiv AI

22h ago

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?

arXiv:2605.30557v2 Announce Type: replace-cross Abstract: Spatial reasoning benchmarks typically evaluate whether vision-language models can derive the correct answer from a visual observation. Yet i...

By Yue Zhang, Zun Wang, Han Lin, Yonatan Bitton, Idan Szpektor, Mohit Bansal

llms fine-tuning multimodal benchmarks

arXiv AI

Jun 9

SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks

arXiv:2606. 09669v1 Announce Type: new Abstract: Spatial reasoning is a foundational capability for multimodal large language models (MLLMs) to perceive and operate within the physical world.

By Hongcheng Gao, Hailong Qu, Jingyi Tang, Jiahao Wang, Zihao Huang, Hengkang Qiao, Shihong Huang, Junming Yang, Yi Li, Hongyixuan Yuan, Wenjie Li, Bohan Zeng, Wenbo Li, Bo Wang, Jianhui Liu, Olive Huang, Haoyang Huang, Wentao Zhang, Guoqing Huang, Nan Duan, Yinpeng Dong

llms agents multimodal benchmarks

arXiv Computation and Language

Sep 25

STRAND: Benchmarking and Improving Object-Centric Spatio-Temporal Monitoring in Video Large Language Models

STRAND is a new benchmark that tests multimodal large language models’ ability to track objects, their states, and relationships over time in videos. It evaluates intermediate reasoning by breaking queries into sub‑questions and uses Faithful Accuracy to ensure all parts of an answer are correct. The authors also propose an object‑centric framework that builds structured trajectories and shows reduced hallucinations and better temporal consistency compared to existing models.

By Thong Nguyen, Tri Cao, Khoi Le, Cong-Duy Nguyen, Quynh Vo, See-Kiong Ng, Bryan Hooi Kuen-Yew

llms multimodal benchmarks safety

arXiv AI

Jul 31

See2Think: Do Multimodal Models Really Use Intermediate Visual States?

arXiv:2607. 26769v1 Announce Type: cross Abstract: Multimodal large language models increasingly use sketches, annotations, tools, and intermediate images during reasoning, but it remains unclear whether they truly rely on these visual states.

By Siyu Yan, Zhuoran Yan, Haiying Xu, Panhao Zhou, Jingyu Chen, Chenhao Ji, Shuo Cao, Yongheng Zhang, Haoze Liu, Siyu Zhang, Xiwen Gu, Yihao Liu, Alex Jinpeng Wang

llms multimodal benchmarks

arXiv AI

Jun 3

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

arXiv:2606. 03988v1 Announce Type: new Abstract: Vision language models (VLMs) excel at many tasks but still struggle with spatial reasoning when critical information is not directly observable.

By Mahtab Bigverdi, Lindsey Li, Weikai Huang, Yiming Liu, Jaemin Cho, Jieyu Zhang, Tuhin Kundu, Chris Dangjoo Kim, Zelun Luo, Linda Shapiro, Ranjay Krishna

llms multimodal benchmarks

One email a morning, machine-written

Related stories

Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?

SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks

STRAND: Benchmarking and Improving Object-Centric Spatio-Temporal Monitoring in Video Large Language Models

See2Think: Do Multimodal Models Really Use Intermediate Visual States?

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models