DUEL: Adversarial Self-Play for Multimodal Reasoning 事件

DUEL: Adversarial Self-Play for Multimodal Reasoning arXiv:2605.24794v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as an effective paradigm for improving the reasoning capability of vision-language models (VLMs). However, RL-based optimization typically depends on costly high-quality annotations that are difficult to scale. Existing unsupervised alternatives may drift toward biased solutions due to weak visual grounding and the lack of reliable verification signals. We