Saved in:
Bibliographic Details
Main Authors: 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
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!
Table of 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.