Multimodal Stance Detection (MSD) is crucial for understanding public discourse, yet effectively fusing text and image, especially with conflicting signals, remains challenging. Existing methods often face difficulties with contextual grounding, cross-modal interpretation ambiguity, and single-pass reasoning fragility. To address these, we propose Retrieval-Augmented Multi-modal Multi-agent Stance Detection (MM-StanceDet), a novel multi-agent framework integrating Retrieval Augmentation for contextual grounding, specialized Multimodal Analysis agents for nuanced interpretation, a Reasoning-Enhanced Debate stage for exploring perspectives, and Self-Reflection for robust adjudication. Extensive experiments on five datasets demonstrate MM-StanceDet significantly outperforms state-of-the-art baselines, validating the efficacy of its multi-agent architecture and structured reasoning stages in addressing complex multimodal stance challenges.
@article{arxiv.2604.27934,
title = {MM-StanceDet: Retrieval-Augmented Multi-modal Multi-agent Stance Detection},
author = {Weihai Lu and Zhejun Zhao and Yanshu Li and Huan He},
journal= {arXiv preprint arXiv:2604.27934},
year = {2026}
}