When Does a Video-Language Model Stop Watching? Reward Strength Controls the Formation and Reversal of Visual Shortcuts in Multimodal RLVR (opens in new tab)

Reinforcement learning with verifiable rewards (RLVR) is increasingly applied to large vision-language models (LVLMs), yet outcome-only optimization can drive a model to stop attending to the video and instead exploit linguistic priors -- a failure we call a visual shortcut. While the existence of such perception bypass is by now documented, how it forms, whether it can be undone, and when intervention still helps remain open. We treat the stren...