SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning

Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-correction, especially compared to their unimodal text-based counterparts. Existing reflection methods are simplistic and struggle to generate meaningful and instructive feedback, as the reasoning ability and knowledge limits of pre-trained models are largely fixed during initial training. To overcome these challenges, we propose Multimodal Self-Reflection enhanced reasoning with Group Relative Policy Optimization (SRPO), a two-stage reflection-aware reinforcement learning (RL) framework explicitly designed to enhance multimodal LLM reasoning. In the first stage, we construct a high-quality, reflection-focused dataset under the guidance of an advanced MLLM, which generates reflections based on initial responses to help the policy model learn both reasoning and self-reflection. In the second stage, we introduce a novel reward mechanism within the GRPO framework that encourages concise and cognitively meaningful reflection while avoiding redundancy. Extensive experiments across multiple multimodal reasoning benchmarks, including MathVista, MathVision, MathVerse, and MMMU-Pro, using Qwen-2.5-VL-7B and Qwen-2.5-VL-32B demonstrate that SRPO significantly outperforms state-of-the-art models, achieving notable improvements in both reasoning accuracy and reflection quality.

@article{wan2025_2506.01713,
  title={ SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning },
  author={ Zhongwei Wan and Zhihao Dou and Che Liu and Yu Zhang and Dongfei Cui and Qinjian Zhao and Hui Shen and Jing Xiong and Yi Xin and Yifan Jiang and Chaofan Tao and Yangfan He and Mi Zhang and Shen Yan },
  journal={arXiv preprint arXiv:2506.01713},
  year={ 2025 }
}