Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916747340152832 |
|---|---|
| author | Zhou, Guanghao Qiu, Panjia Chen, Cen Wang, Jie Yang, Zheming Xu, Jian Qiu, Minghui |
| author_facet | Zhou, Guanghao Qiu, Panjia Chen, Cen Wang, Jie Yang, Zheming Xu, Jian Qiu, Minghui |
| contents | The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area. While MLLMs extend Large Language Models (LLMs) to handle diverse modalities such as vision, audio, and video, enabling robust reasoning across multimodal inputs remains challenging. This paper provides a systematic review of recent advances in RL-based reasoning for MLLMs, covering key algorithmic designs, reward mechanism innovations, and practical applications. We highlight two main RL paradigms, value-model-free and value-model-based methods, and analyze how RL enhances reasoning abilities by optimizing reasoning trajectories and aligning multimodal information. Additionally, we provide an extensive overview of benchmark datasets, evaluation protocols, and current limitations, and propose future research directions to address challenges such as sparse rewards, inefficient cross-modal reasoning, and real-world deployment constraints. Our goal is to provide a comprehensive and structured guide to RL-based multimodal reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_21277 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models Zhou, Guanghao Qiu, Panjia Chen, Cen Wang, Jie Yang, Zheming Xu, Jian Qiu, Minghui Artificial Intelligence The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area. While MLLMs extend Large Language Models (LLMs) to handle diverse modalities such as vision, audio, and video, enabling robust reasoning across multimodal inputs remains challenging. This paper provides a systematic review of recent advances in RL-based reasoning for MLLMs, covering key algorithmic designs, reward mechanism innovations, and practical applications. We highlight two main RL paradigms, value-model-free and value-model-based methods, and analyze how RL enhances reasoning abilities by optimizing reasoning trajectories and aligning multimodal information. Additionally, we provide an extensive overview of benchmark datasets, evaluation protocols, and current limitations, and propose future research directions to address challenges such as sparse rewards, inefficient cross-modal reasoning, and real-world deployment constraints. Our goal is to provide a comprehensive and structured guide to RL-based multimodal reasoning. |
| title | Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2504.21277 |