arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.03586cs.CL
收藏

MultiPress:一种用于可解释多模态新闻分类的多智能体框架

MultiPress: A Multi-Agent Framework for Interpretable Multimodal News Classification

New York Institute of Technology(纽约理工学院);University of Arizona(亚利桑那大学);University of Macau(澳门大学);Peking University(北京大学);Juniata College(朱尼亚塔学院)

Tailong Luo, Hao Li, Rong Fu, Xinyue Jiang, Huaxuan Ding, Yiduo Zhang, Zilin Zhao, Simon Fong, Guangyin Jin, Jianyuan Ni

AI总结:

本文提出MultiPress多智能体框架,通过多模块协作和检索增强推理提升多模态新闻分类的准确性和可解释性。

摘要:

随着多模态新闻内容的普及,有效的新闻主题分类需要能够联合理解和推理异构数据(如文本和图像)的模型。现有方法往往独立处理模态或采用简单融合策略,限制了其捕捉复杂跨模态交互和利用外部知识的能力。为克服这些限制,我们提出MultiPress,一种新颖的三阶段多智能体框架用于多模态新闻分类。MultiPress集成了专门用于多模态感知、检索增强推理和门控融合评分的智能体,随后通过奖励驱动的迭代优化机制。我们在新构建的大型多模态新闻数据集上验证了MultiPress,证明其在强基线上的显著改进,并突显了模块化多智能体协作和检索增强推理在提升分类准确性和可解释性方面的有效性。

英文摘要:

With the growing prevalence of multimodal news content, effective news topic classification demands models capable of jointly understanding and reasoning over heterogeneous data such as text and images. Existing methods often process modalities independently or employ simplistic fusion strategies, limiting their ability to capture complex cross-modal interactions and leverage external knowledge. To overcome these limitations, we propose MultiPress, a novel three-stage multi-agent framework for multimodal news classification. MultiPress integrates specialized agents for multimodal perception, retrieval-augmented reasoning, and gated fusion scoring, followed by a reward-driven iterative optimization mechanism. We validate MultiPress on a newly constructed large-scale multimodal news dataset, demonstrating significant improvements over strong baselines and highlighting the effectiveness of modular multi-agent collaboration and retrieval-augmented reasoning in enhancing classification accuracy and interpretability.

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。

↑