Thinking with Visual Abstract: Enhancing Multimodal Reasoning via Visual Abstraction

TL;DR

This paper introduces Visual Abstract Thinking (VAT), a novel paradigm that improves multimodal reasoning in large language models by focusing on essential visual elements, leading to better performance with fewer tokens.

Contribution

The paper proposes VAT as a new reasoning paradigm that enhances multimodal reasoning by emphasizing visual abstraction, outperforming traditional methods like Chain-of-Thought.

Findings

VAT improves multimodal reasoning performance by 2.21% over GPT-5 baseline.

VAT requires fewer tokens while achieving higher accuracy.

VAT outperforms Chain-of-Thought in visual perception tasks.

Abstract

Images usually convey richer detail than text, but often include redundant information, which potentially downgrades multimodal reasoning performance. When faced with lengthy or complex messages, humans tend to employ abstract thinking to convert them into simple and concise abstracts. Inspired by this cognitive strategy, we introduce a novel paradigm to elicit the ability to Think with Visual Abstract (VAT), by prompting Multimodal Large Language Models (MLLMs) with visual abstract instead of explicit verbal thoughts or elaborate guidance, permitting a more efficient visual reasoning mechanism via concentrated perception. VAT encourages models to focus on more essential visual elements, concepts and structural features by undermining redundant information compared with explicit thinking methods, such as Chain-of-thought (CoT) and tool-using approaches, that increase the complexity of reasoning process via inserting verbose intermediate steps and external knowledge. Experimental results show that VAT consistently empowers different MLLMs in visual perception and reasoning tasks. VAT achieves an average gain of $2.21\%$ over GPT-5 baseline, surpassing the gain of CoT, demonstrating that VAT better enhances multimodal task performance of MLLMs. Additionally, VAT spends fewer tokens while achieving higher performance. These findings highlight the effectiveness of visual abstract thinking and encourage further exploration of more diverse reasoning paradigms from the perspective of human cognition.