Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
It provides a structured guide for researchers working on improving reasoning in MLLMs, but it is incremental as it reviews existing work rather than introducing new methods.
This paper surveys recent advances in applying reinforcement learning (RL) to enhance reasoning in Multimodal Large Language Models (MLLMs), covering algorithmic designs, reward mechanisms, and applications, while identifying challenges like sparse rewards and proposing future directions.
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.