Saved in:
Bibliographic Details
Main Authors: Lin, Zhiyu, Gao, Yifei, Zhao, Xian, Yang, Yunfan, Sang, Jitao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.18071
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908280124604416
author Lin, Zhiyu
Gao, Yifei
Zhao, Xian
Yang, Yunfan
Sang, Jitao
author_facet Lin, Zhiyu
Gao, Yifei
Zhao, Xian
Yang, Yunfan
Sang, Jitao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18071
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mind with Eyes: from Language Reasoning to Multimodal Reasoning
Lin, Zhiyu
Gao, Yifei
Zhao, Xian
Yang, Yunfan
Sang, Jitao
Computation and Language
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.
title Mind with Eyes: from Language Reasoning to Multimodal Reasoning
topic Computation and Language
url https://arxiv.org/abs/2503.18071