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

Source: [MultiPress: A Multi-Agent Framework for Interpretable Multimodal News Classification](<https://www.sota2.com/research/paper/69d48f5e7d0172140ec74110>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-08T05:00:04.658Z

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

Published: 2026-04-04T04:25:26.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multimodal News Classification on NewsMM (test)](<https://www.sota2.com/research/sota/multimodal-news-classification-on-newsmm-test.md>): Multimodal News Classification; NewsMM (test); Accuracy: 91.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.03586>)

[PDF](<https://arxiv.org/pdf/2604.03586.pdf>)
