English

Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning

Computer Vision and Pattern Recognition 2026-03-31 v1 Artificial Intelligence

Abstract

Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual access. Inspired by human visual perception-where attention is selectively and sequentially shifted from the most informative regions to secondary cues-we propose Structural Sequential Visual CoT SSV-CoT. First, a question-relevant saliency map identifies and organizes key visual regions, explicitly modeling the spatial distribution of visual importance. Second, reasoning is performed following this discriminative order, inducing a curriculum-like semantic progression from primary to secondary cues. This method is trained end-to-end, using text cot and answer supervision, without relying on region-level annotations or specialized external tools. Experiments on diverse visual reasoning benchmarks show gains, validating structured and sequential visual cognition.

Keywords

Cite

@article{arxiv.2603.26737,
  title  = {Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning},
  author = {Guangfu Guo and Xiaoqian Lu and Yue Feng and Mingming Sun},
  journal= {arXiv preprint arXiv:2603.26737},
  year   = {2026}
}
R2 v1 2026-07-01T11:41:24.511Z