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

Zhongwei Wan, Zhihao Dou, liu, Yu Zhang, Dongfei Cui, Albert Zhao , Hui Shen, Jing Xiong, Yi Xin, Yifan Jiang, Yangfan He, Mi Zhang, Shen Yan

SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning: 48 upvotes on Hugging Face Daily Papers, #6 of 62 papers on 2025-06-03. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.