Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.23802 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917299289587712 |
|---|---|
| author | Fang, Yiyang Huang, Wenke Fu, Pei Yang, Yihao Su, Kehua Luo, Zhenbo Luan, Jian Ye, Mang |
| author_facet | Fang, Yiyang Huang, Wenke Fu, Pei Yang, Yihao Su, Kehua Luo, Zhenbo Luan, Jian Ye, Mang |
| contents | Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual reasoning and understanding tasks but still struggle to capture the complexity and subjectivity of human emotions. Existing approaches based on supervised fine-tuning often suffer from limited generalization and poor interpretability, while reinforcement learning methods such as Group Relative Policy Optimization fail to align with the intrinsic characteristics of emotional cognition. To address these challenges, we propose Reflective Reinforcement Learning for Emotional Reasoning (EMO-R3), a framework designed to enhance the emotional reasoning ability of MLLMs. Specifically, we introduce Structured Emotional Thinking to guide the model to perform step-by-step emotional reasoning in a structured and interpretable manner, and design a Reflective Emotional Reward that enables the model to re-evaluate its reasoning based on visual-text consistency and emotional coherence. Extensive experiments demonstrate that EMO-R3 significantly improves both the interpretability and emotional intelligence of MLLMs, achieving superior performance across multiple visual emotional understanding benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23802 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Fang, Yiyang Huang, Wenke Fu, Pei Yang, Yihao Su, Kehua Luo, Zhenbo Luan, Jian Ye, Mang Artificial Intelligence Computer Vision and Pattern Recognition Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual reasoning and understanding tasks but still struggle to capture the complexity and subjectivity of human emotions. Existing approaches based on supervised fine-tuning often suffer from limited generalization and poor interpretability, while reinforcement learning methods such as Group Relative Policy Optimization fail to align with the intrinsic characteristics of emotional cognition. To address these challenges, we propose Reflective Reinforcement Learning for Emotional Reasoning (EMO-R3), a framework designed to enhance the emotional reasoning ability of MLLMs. Specifically, we introduce Structured Emotional Thinking to guide the model to perform step-by-step emotional reasoning in a structured and interpretable manner, and design a Reflective Emotional Reward that enables the model to re-evaluate its reasoning based on visual-text consistency and emotional coherence. Extensive experiments demonstrate that EMO-R3 significantly improves both the interpretability and emotional intelligence of MLLMs, achieving superior performance across multiple visual emotional understanding benchmarks. |
| title | EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.23802 |