AutoGen-Powered Multi-Agent Framework for Interpretable Multimodal Emotion Recognition
Year: 2025
Type: conference-paper
Abstract: Emotion recognition allows intelligent systems to perceive and respond to human emotions. Single-modal methods often lack robustness, while multimodal approaches capture affective information more comprehensively. Existing multimodal models, however, struggle with modality heterogeneity, conflict resolution, and interpretability. To address this, we propose an AutoGen-based multi-agent framework, where expert agents for text, audio, video, fusion, and quality control collaborate through conflict-driven discussions. Experiments show it outperforms single-modal and conventional multimodal models in accuracy, F1-score, correlation, and robustness, while providing interpretable reasoning pathways.
Authors: Xinting Xu, Tianyu Gao, Rui Zhang, Shengjie Lin
Institution: Zhejiang University of Technology
Topic: Emotion and Mood Recognition
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W4417494408