摘要：思维链推理通过使大语言模型（LLM）能够在作答前将问题分解为中间步骤，彻底改变了自然语言处理。然而，将推理局限于文本领域，对于需要直接操作视觉表征的任务存在局限。近期工作通过深度估计或目标检测模块等外部视觉专家工具增强多模态 LLM，但这些方法从根本上仍受限于狭窄、僵化的操作，无法灵活地生成或变换视觉内容。我们提出 ReImaGin，该方法将图像生成模型作为多模态 LLM 灵活的视觉推理机制：与功能固定的工具不同，图像生成模型能够接受自然语言指令，并执行开放式视觉操作，例如移除遮挡物，或根据房间的多个非连续视角生成平面图。在包括多视角空间推理和碰撞预测在内的六项不同视觉推理任务中，ReImaGin 始终优于纯文本推理和专业视觉工具基线，最高提升达 25%，证明了灵活生成式视觉推理的优势。

Abstract:Chain-of-thought reasoning has revolutionized natural language processing by enabling large language models (LLMs) to decompose problems into intermediate steps before answering. Yet confining reasoning to the textual domain presents limitations for tasks requiring direct manipulation of visual representations. Recent efforts augment multimodal LLMs with external visual expert tools such as depth estimation or object detection modules, but these remain fundamentally limited by their reliance on narrow, rigid operations that cannot flexibly generate or transform visual content. We propose ReImaGin, which leverages image generation models as a flexible visual reasoning mechanism for multimodal LLMs: unlike fixed-function tools, they accept natural language commands and can perform open-ended visual operations, like removing an occlusion or generating a floorplan from multiple disjoint views of a room. Across six diverse visual reasoning tasks including multi-view spatial reasoning and collision prediction, ReImaGin consistently outperforms both text-only reasoning and specialist vision-tool baselines, with gains of up to 25%, demonstrating the advantage of flexible, generative visual reasoning.