@inproceedings{xu-etal-2026-ration,
    title = "{RATION}: Entropy-Driven Task-Adaptive Visual Attention Allocation Framework for Multimodal Reasoning",
    author = "Xu, Xingle  and
      Kong, Fanheng  and
      Cai, Dexian  and
      Feng, Shi  and
      Yang, Xiaocui  and
      Wang, Daling  and
      Zhang, Yifei",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1238/",
    pages = "24726--24744",
    ISBN = "979-8-89176-395-1",
    abstract = "Multimodal Large Language Models (MLLMs) integrate visual encoders with Large Language Models (LLMs) and enable multimodal reasoning. However, for tasks that heavily rely on visual information, the model{'}s utilization of visual information remains unstable, which leads to reasoning failures. Prior works mainly strengthen multimodal reasoning by improving representation alignment or increasing computation. However, these methods do not explicitly characterize the differences in visual demands across tasks, making it difficult for the model to decide where and how strongly to attend to visual information. Consequently, visual attention allocation becomes a key factor that affects multimodal reasoning. To address these, we propose RATION, an entropy-driven task-adaptive visual attention allocation framework. First, we use a task routing strategy to infer the task type of each sample and identify the key layers. We use visual attention entropy as a control signal to dynamically allocate attention according to task demands. Experiments show that RATION achieves consistent performance gains across diverse reasoning tasks, datasets, and models, providing a clear direction toward more reliable multimodal reasoning."
}