English

UnAC: Adaptive Visual Prompting with Abstraction and Stepwise Checking for Complex Multimodal Reasoning

Computer Vision and Pattern Recognition 2026-05-06 v1

Abstract

Although recent LMMs have become much stronger at visual perception, they remain unreliable on problems that require multi-step reasoning over visual evidence. In this paper, we present UnAC (Understanding, Abstracting, and Checking), a multimodal prompting method that strengthens reasoning for complex multimodal tasks in LMMs (e.g., GPT-4o, Gemini 1.5, and GPT-4V). To improve image understanding and capture fine details, we propose an adaptive visual prompting strategy that enables LMMs to focus on salient regions. We further design an image-abstraction prompt to effectively extract key information from images. In addition, we introduce a gradual self-checking scheme that improves reasoning by verifying each decomposed subquestion and its answer. Extensive experiments on three public benchmarks-MathVista, MM-Vet, and MMMU.

Keywords

Cite

@article{arxiv.2605.03950,
  title  = {UnAC: Adaptive Visual Prompting with Abstraction and Stepwise Checking for Complex Multimodal Reasoning},
  author = {Yifan Wang and Yun Fu},
  journal= {arXiv preprint arXiv:2605.03950},
  year   = {2026}
}
R2 v1 2026-07-01T12:51:10.385Z