MentisOculi: Revealing the Limits of Reasoning with Mental Imagery
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914301817651200 |
|---|---|
| author | Zeller, Jana Wiedemer, Thaddäus Li, Fanfei Klein, Thomas Mayilvahanan, Prasanna Bethge, Matthias Wichmann, Felix Cotterell, Ryan Brendel, Wieland |
| author_facet | Zeller, Jana Wiedemer, Thaddäus Li, Fanfei Klein, Thomas Mayilvahanan, Prasanna Bethge, Matthias Wichmann, Felix Cotterell, Ryan Brendel, Wieland |
| contents | Frontier models are transitioning from multimodal large language models (MLLMs) that merely ingest visual information to unified multimodal models (UMMs) capable of native interleaved generation. This shift has sparked interest in using intermediate visualizations as a reasoning aid, akin to human mental imagery. Central to this idea is the ability to form, maintain, and manipulate visual representations in a goal-oriented manner. To evaluate and probe this capability, we develop MentisOculi, a procedural, stratified suite of multi-step reasoning problems amenable to visual solution, tuned to challenge frontier models. Evaluating visual strategies ranging from latent tokens to explicit generated imagery, we find they generally fail to improve performance. Analysis of UMMs specifically exposes a critical limitation: While they possess the textual reasoning capacity to solve a task and can sometimes generate correct visuals, they suffer from compounding generation errors and fail to leverage even ground-truth visualizations. Our findings suggest that despite their inherent appeal, visual thoughts do not yet benefit model reasoning. MentisOculi establishes the necessary foundation to analyze and close this gap across diverse model families. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02465 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MentisOculi: Revealing the Limits of Reasoning with Mental Imagery Zeller, Jana Wiedemer, Thaddäus Li, Fanfei Klein, Thomas Mayilvahanan, Prasanna Bethge, Matthias Wichmann, Felix Cotterell, Ryan Brendel, Wieland Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Frontier models are transitioning from multimodal large language models (MLLMs) that merely ingest visual information to unified multimodal models (UMMs) capable of native interleaved generation. This shift has sparked interest in using intermediate visualizations as a reasoning aid, akin to human mental imagery. Central to this idea is the ability to form, maintain, and manipulate visual representations in a goal-oriented manner. To evaluate and probe this capability, we develop MentisOculi, a procedural, stratified suite of multi-step reasoning problems amenable to visual solution, tuned to challenge frontier models. Evaluating visual strategies ranging from latent tokens to explicit generated imagery, we find they generally fail to improve performance. Analysis of UMMs specifically exposes a critical limitation: While they possess the textual reasoning capacity to solve a task and can sometimes generate correct visuals, they suffer from compounding generation errors and fail to leverage even ground-truth visualizations. Our findings suggest that despite their inherent appeal, visual thoughts do not yet benefit model reasoning. MentisOculi establishes the necessary foundation to analyze and close this gap across diverse model families. |
| title | MentisOculi: Revealing the Limits of Reasoning with Mental Imagery |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2602.02465 |