Thinking with Comics: Enhancing Multimodal Reasoning through Structured Visual Storytelling

TL;DR

This paper introduces 'Thinking with Comics,' a novel multimodal reasoning paradigm using comics as an intermediate visual medium that balances information density, temporal structure, and computational efficiency, outperforming images and videos.

Contribution

The work systematically studies comic-based reasoning paths, demonstrating their effectiveness and efficiency in multimodal reasoning tasks compared to traditional images and videos.

Findings

Comics outperform images in multi-step temporal and causal reasoning.

Comics are more efficient than videos for reasoning tasks.

Different comic styles influence reasoning performance.

Abstract

Chain-of-Thought reasoning has driven large language models to extend from thinking with text to thinking with images and videos. However, different modalities still have clear limitations: static images struggle to represent temporal structure, while videos introduce substantial redundancy and computational cost. In this work, we propose Thinking with Comics, a visual reasoning paradigm that uses comics as a high information-density medium positioned between images and videos. Comics preserve temporal structure, embedded text, and narrative coherence while requiring significantly lower reasoning cost. We systematically study two reasoning paths based on comics and evaluate them on a range of reasoning tasks and long-context understanding tasks. Experimental results show that Thinking with Comics outperforms Thinking with Images on multi-step temporal and causal reasoning tasks, while remaining substantially more efficient than Thinking with Video. Further analysis indicates that different comic narrative structures and styles consistently affect performance across tasks, suggesting that comics serve as an effective intermediate visual representation for improving multimodal reasoning.