Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912462815625216 |
|---|---|
| author | Su, Zhaochen Xia, Peng Guo, Hangyu Liu, Zhenhua Ma, Yan Qu, Xiaoye Liu, Jiaqi Li, Yanshu Zeng, Kaide Yang, Zhengyuan Li, Linjie Cheng, Yu Ji, Heng He, Junxian Fung, Yi R. |
| author_facet | Su, Zhaochen Xia, Peng Guo, Hangyu Liu, Zhenhua Ma, Yan Qu, Xiaoye Liu, Jiaqi Li, Yanshu Zeng, Kaide Yang, Zhengyuan Li, Linjie Cheng, Yu Ji, Heng He, Junxian Fung, Yi R. |
| contents | Recent progress in multimodal reasoning has been significantly advanced by textual Chain-of-Thought (CoT), a paradigm where models conduct reasoning within language. This text-centric approach, however, treats vision as a static, initial context, creating a fundamental "semantic gap" between rich perceptual data and discrete symbolic thought. Human cognition often transcends language, utilizing vision as a dynamic mental sketchpad. A similar evolution is now unfolding in AI, marking a fundamental paradigm shift from models that merely think about images to those that can truly think with images. This emerging paradigm is characterized by models leveraging visual information as intermediate steps in their thought process, transforming vision from a passive input into a dynamic, manipulable cognitive workspace. In this survey, we chart this evolution of intelligence along a trajectory of increasing cognitive autonomy, which unfolds across three key stages: from external tool exploration, through programmatic manipulation, to intrinsic imagination. To structure this rapidly evolving field, our survey makes four key contributions. (1) We establish the foundational principles of the think with image paradigm and its three-stage framework. (2) We provide a comprehensive review of the core methods that characterize each stage of this roadmap. (3) We analyze the critical landscape of evaluation benchmarks and transformative applications. (4) We identify significant challenges and outline promising future directions. By providing this structured overview, we aim to offer a clear roadmap for future research towards more powerful and human-aligned multimodal AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23918 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers Su, Zhaochen Xia, Peng Guo, Hangyu Liu, Zhenhua Ma, Yan Qu, Xiaoye Liu, Jiaqi Li, Yanshu Zeng, Kaide Yang, Zhengyuan Li, Linjie Cheng, Yu Ji, Heng He, Junxian Fung, Yi R. Computer Vision and Pattern Recognition Recent progress in multimodal reasoning has been significantly advanced by textual Chain-of-Thought (CoT), a paradigm where models conduct reasoning within language. This text-centric approach, however, treats vision as a static, initial context, creating a fundamental "semantic gap" between rich perceptual data and discrete symbolic thought. Human cognition often transcends language, utilizing vision as a dynamic mental sketchpad. A similar evolution is now unfolding in AI, marking a fundamental paradigm shift from models that merely think about images to those that can truly think with images. This emerging paradigm is characterized by models leveraging visual information as intermediate steps in their thought process, transforming vision from a passive input into a dynamic, manipulable cognitive workspace. In this survey, we chart this evolution of intelligence along a trajectory of increasing cognitive autonomy, which unfolds across three key stages: from external tool exploration, through programmatic manipulation, to intrinsic imagination. To structure this rapidly evolving field, our survey makes four key contributions. (1) We establish the foundational principles of the think with image paradigm and its three-stage framework. (2) We provide a comprehensive review of the core methods that characterize each stage of this roadmap. (3) We analyze the critical landscape of evaluation benchmarks and transformative applications. (4) We identify significant challenges and outline promising future directions. By providing this structured overview, we aim to offer a clear roadmap for future research towards more powerful and human-aligned multimodal AI. |
| title | Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.23918 |