Mind with Eyes：从语言推理到多模态推理
Mind with Eyes: from Language Reasoning to Multimodal Reasoning
AI总结：
该综述系统梳理多模态推理研究，将现有方法分为以语言为中心和协同式两类，分析技术演进与挑战，介绍相关基准与指标，并提出全模态推理、多模态智能体两大未来研究方向。
摘要：
语言模型近年来已拓展至推理领域，然而唯有通过多模态推理，我们才能充分释放潜力，实现更全面、类人的认知能力。本综述系统梳理了近期的多模态推理方法，将其划分为两个层级：以语言为中心的多模态推理与协同式多模态推理。前者涵盖单次视觉感知与主动视觉感知，视觉在其中主要为语言推理提供支撑作用。后者则涉及推理过程中的动作生成与状态更新，可实现模态间更动态的交互。此外，我们分析了这些方法的技术演进路径，讨论了其固有挑战，并介绍了用于评估多模态推理性能的关键基准任务与评价指标。最后，我们从以下两个视角提出了未来研究方向的洞见：（i）从视觉-语言推理到全模态推理；（ii）从多模态推理到多模态智能体。本综述旨在提供一份结构化的梳理，为多模态推理研究的进一步发展提供启发。
英文摘要：
Language models have recently advanced into the realm of reasoning, yet it is through multimodal reasoning that we can fully unlock the potential to achieve more comprehensive, human-like cognitive capabilities. This survey provides a systematic overview of the recent multimodal reasoning approaches, categorizing them into two levels: language-centric multimodal reasoning and collaborative multimodal reasoning. The former encompasses one-pass visual perception and active visual perception, where vision primarily serves a supporting role in language reasoning. The latter involves action generation and state update within reasoning process, enabling a more dynamic interaction between modalities. Furthermore, we analyze the technical evolution of these methods, discuss their inherent challenges, and introduce key benchmark tasks and evaluation metrics for assessing multimodal reasoning performance. Finally, we provide insights into future research directions from the following two perspectives: (i) from visual-language reasoning to omnimodal reasoning and (ii) from multimodal reasoning to multimodal agents. This survey aims to provide a structured overview that will inspire further advancements in multimodal reasoning research.
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。
