AI RESEARCH
RESP: Reference-guided Sequential Prompting for Visual Glitch Detection in Video Games
arXiv CS.CV
•
ArXi:2604.11082v1 Announce Type: new Visual glitches in video games degrade player experience and perceived quality, yet manual quality assurance cannot scale to the growing test surface of modern game development. Prior automation efforts, particularly those using vision-language models (VLMs), largely operate on single frames or rely on limited video-level baselines that struggle under realistic scene variation, making robust video-level glitch detection challenging. We present RESP, a practical multi-frame framework for gameplay glitch detection with VLMs.