Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.04460 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918253742260224 |
|---|---|
| author | Qiao, Runqi Tan, Qiuna Yang, Minghan Dong, Guanting Yang, Peiqing Lang, Shiqiang Wan, Enhui Wang, Xiaowan Xu, Yida Yang, Lan Sun, Chong Li, Chen Lyu, Jing Zhang, Honggang |
| author_facet | Qiao, Runqi Tan, Qiuna Yang, Minghan Dong, Guanting Yang, Peiqing Lang, Shiqiang Wan, Enhui Wang, Xiaowan Xu, Yida Yang, Lan Sun, Chong Li, Chen Lyu, Jing Zhang, Honggang |
| contents | Empowering Large Multimodal Models (LMMs) to deeply integrate image interaction with long-horizon reasoning capabilities remains a long-standing challenge in this field. Recent advances in vision-centric reasoning explore a promising "Thinking with Images" paradigm for LMMs, marking a shift from image-assisted reasoning to image-interactive thinking. While this milestone enables models to focus on fine-grained image regions, progress remains constrained by limited visual tool spaces and task-specific workflow designs. To bridge this gap, we present V-Thinker, a general-purpose multimodal reasoning assistant that enables interactive, vision-centric thinking through end-to-end reinforcement learning. V-Thinker comprises two key components: (1) a Data Evolution Flywheel that automatically synthesizes, evolves, and verifies interactive reasoning datasets across three dimensions-diversity, quality, and difficulty; and (2) a Visual Progressive Training Curriculum that first aligns perception via point-level supervision, then integrates interactive reasoning through a two-stage reinforcement learning framework. Furthermore, we introduce VTBench, an expert-verified benchmark targeting vision-centric interactive reasoning tasks. Extensive experiments demonstrate that V-Thinker consistently outperforms strong LMM-based baselines in both general and interactive reasoning scenarios, providing valuable insights for advancing image-interactive reasoning applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_04460 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | V-Thinker: Interactive Thinking with Images Qiao, Runqi Tan, Qiuna Yang, Minghan Dong, Guanting Yang, Peiqing Lang, Shiqiang Wan, Enhui Wang, Xiaowan Xu, Yida Yang, Lan Sun, Chong Li, Chen Lyu, Jing Zhang, Honggang Computer Vision and Pattern Recognition Empowering Large Multimodal Models (LMMs) to deeply integrate image interaction with long-horizon reasoning capabilities remains a long-standing challenge in this field. Recent advances in vision-centric reasoning explore a promising "Thinking with Images" paradigm for LMMs, marking a shift from image-assisted reasoning to image-interactive thinking. While this milestone enables models to focus on fine-grained image regions, progress remains constrained by limited visual tool spaces and task-specific workflow designs. To bridge this gap, we present V-Thinker, a general-purpose multimodal reasoning assistant that enables interactive, vision-centric thinking through end-to-end reinforcement learning. V-Thinker comprises two key components: (1) a Data Evolution Flywheel that automatically synthesizes, evolves, and verifies interactive reasoning datasets across three dimensions-diversity, quality, and difficulty; and (2) a Visual Progressive Training Curriculum that first aligns perception via point-level supervision, then integrates interactive reasoning through a two-stage reinforcement learning framework. Furthermore, we introduce VTBench, an expert-verified benchmark targeting vision-centric interactive reasoning tasks. Extensive experiments demonstrate that V-Thinker consistently outperforms strong LMM-based baselines in both general and interactive reasoning scenarios, providing valuable insights for advancing image-interactive reasoning applications. |
| title | V-Thinker: Interactive Thinking with Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.04460 |