When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning
This addresses the scalability issue in training multimodal models for reasoning tasks, offering a potential path toward self-evolving systems without human supervision.
The paper tackles the problem of costly and unscalable reliance on annotated data or teacher models for improving multimodal reasoning by proposing an unsupervised self-evolution framework, achieving stable performance improvements on five mathematical reasoning benchmarks.
Recent progress in multimodal large language models has led to strong performance on reasoning tasks, but these improvements largely rely on high-quality annotated data or teacher-model distillation, both of which are costly and difficult to scale. To address this, we propose an unsupervised self-evolution training framework for multimodal reasoning that achieves stable performance improvements without using human-annotated answers or external reward models. For each input, we sample multiple reasoning trajectories and jointly model their within group structure. We use the Actor's self-consistency signal as a training prior, and introduce a bounded Judge based modulation to continuously reweight trajectories of different quality. We further model the modulated scores as a group level distribution and convert absolute scores into relative advantages within each group, enabling more robust policy updates. Trained with Group Relative Policy Optimization (GRPO) on unlabeled data, our method consistently improves reasoning performance and generalization on five mathematical reasoning benchmarks, offering a scalable path toward self-evolving multimodal models. The code are available at https://github.com/OPPO-Mente-Lab/LLM-Self-Judge.