用漫画思考：通过结构化视觉叙事增强多模态推理
Thinking with Comics: Enhancing Multimodal Reasoning through Structured Visual Storytelling
AI总结：
本文提出用漫画作为中间视觉表示，通过结构化视觉叙事提升多模态推理效率和性能。
摘要：
链式推理推动大语言模型从文本思考扩展到图像和视频思考。然而，不同模态仍有明显局限：静态图像难以表示时间结构，而视频引入了大量冗余和计算成本。在本工作中，我们提出了Thinking with Comics，一种使用漫画作为高信息密度介质的视觉推理范式，该介质介于图像和视频之间。漫画保留了时间结构、嵌入文本和叙事连贯性，同时要求显著较低的推理成本。我们系统研究了基于漫画的两种推理路径，并在多种推理任务和长上下文理解任务上进行了评估。实验结果表明，Thinking with Comics在多步时间与因果推理任务上优于Thinking with Images，同时比Thinking with Video效率高得多。进一步分析表明，不同的漫画叙事结构和风格在任务中一致影响性能，这表明漫画作为一种有效的中间视觉表示，能够提升多模态推理。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
