From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912650879827968 |
|---|---|
| author | Zhou, Chenyue Wang, Mingxuan Ma, Yanbiao Wu, Chenxu Chen, Wanyi Qian, Zhe Liu, Xinyu Zhang, Yiwei Wang, Junhao Xu, Hengbo Luo, Fei Chen, Xiaohua Hao, Xiaoshuai Li, Hehan Zhang, Andi Wang, Wenxuan Zhang, Kaiyan Jia, Guoli Li, Lingling Lu, Zhiwu Lu, Yang Guo, Yike |
| author_facet | Zhou, Chenyue Wang, Mingxuan Ma, Yanbiao Wu, Chenxu Chen, Wanyi Qian, Zhe Liu, Xinyu Zhang, Yiwei Wang, Junhao Xu, Hengbo Luo, Fei Chen, Xiaohua Hao, Xiaoshuai Li, Hehan Zhang, Andi Wang, Wenxuan Zhang, Kaiyan Jia, Guoli Li, Lingling Lu, Zhiwu Lu, Yang Guo, Yike |
| contents | Multimodal Large Language Models (MLLMs) strive to achieve a profound, human-like understanding of and interaction with the physical world, but often exhibit a shallow and incoherent integration when acquiring information (Perception) and conducting reasoning (Cognition). This disconnect leads to a spectrum of reasoning failures, with hallucination being the most prominent. Collectively, these issues expose a fundamental challenge: the ability to process pixels does not yet confer the ability to construct a coherent, credible internal world model. To systematically dissect and address this challenge, this survey introduces a novel and unified analytical framework: ``From Perception to Cognition." We deconstruct the complex process of vision-language interactive understanding into two interdependent layers: Perception, the foundational ability to accurately extract visual information and achieve fine-grained alignment with textual instructions; and Cognition, the higher-order capability for proactive, multi-step, goal-oriented reasoning built upon this perceptual foundation, the core of which is the formation of a dynamic observe-think-verify reasoning loop. Guided by this framework, this paper systematically analyzes the key bottlenecks of current MLLMs at both layers. It surveys the landscape of cutting-edge methods designed to address these challenges, spanning from techniques that enhance low-level visual representations to those that improve high-level reasoning paradigms. Furthermore, we review critical benchmarks and delineate future research directions. This survey aims to provide the research community with a clear, structured perspective for understanding the intrinsic limitations of current MLLMs and to illuminate the path toward building next-generation models capable of deep reasoning and a genuine understanding of the world. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25373 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models Zhou, Chenyue Wang, Mingxuan Ma, Yanbiao Wu, Chenxu Chen, Wanyi Qian, Zhe Liu, Xinyu Zhang, Yiwei Wang, Junhao Xu, Hengbo Luo, Fei Chen, Xiaohua Hao, Xiaoshuai Li, Hehan Zhang, Andi Wang, Wenxuan Zhang, Kaiyan Jia, Guoli Li, Lingling Lu, Zhiwu Lu, Yang Guo, Yike Artificial Intelligence Multimodal Large Language Models (MLLMs) strive to achieve a profound, human-like understanding of and interaction with the physical world, but often exhibit a shallow and incoherent integration when acquiring information (Perception) and conducting reasoning (Cognition). This disconnect leads to a spectrum of reasoning failures, with hallucination being the most prominent. Collectively, these issues expose a fundamental challenge: the ability to process pixels does not yet confer the ability to construct a coherent, credible internal world model. To systematically dissect and address this challenge, this survey introduces a novel and unified analytical framework: ``From Perception to Cognition." We deconstruct the complex process of vision-language interactive understanding into two interdependent layers: Perception, the foundational ability to accurately extract visual information and achieve fine-grained alignment with textual instructions; and Cognition, the higher-order capability for proactive, multi-step, goal-oriented reasoning built upon this perceptual foundation, the core of which is the formation of a dynamic observe-think-verify reasoning loop. Guided by this framework, this paper systematically analyzes the key bottlenecks of current MLLMs at both layers. It surveys the landscape of cutting-edge methods designed to address these challenges, spanning from techniques that enhance low-level visual representations to those that improve high-level reasoning paradigms. Furthermore, we review critical benchmarks and delineate future research directions. This survey aims to provide the research community with a clear, structured perspective for understanding the intrinsic limitations of current MLLMs and to illuminate the path toward building next-generation models capable of deep reasoning and a genuine understanding of the world. |
| title | From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.25373 |