RESP: Reference-guided Sequential Prompting for Visual Glitch Detection in Video Games

TL;DR

RESP introduces a reference-guided sequential prompting framework using vision-language models to improve video-level glitch detection in video games, addressing limitations of prior single-frame methods.

Contribution

The paper proposes a novel reference-guided prompting approach that enhances robustness in video glitch detection without fine-tuning VLMs, validated on synthetic and real datasets.

Findings

Reference guidance improves frame-level glitch detection across multiple VLMs.

The method achieves stronger video-level triage in realistic QA scenarios.

Experiments demonstrate consistent performance gains across datasets.

Abstract

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. Our key idea is reference-guided prompting: for each test frame, we select a reference frame from earlier in the same video, establishing a visual baseline and reframing detection as within-video comparison rather than isolated classification. RESP sequentially prompts the VLM with reference/test pairs and aggregates noisy frame predictions into a stable video-level decision without fine-tuning the VLM. To enable controlled analysis of reference effects, we introduce RefGlitch, a synthetic dataset of manually labeled reference/test frame pairs with balanced coverage across five glitch types. Experiments across five VLMs and three datasets (one synthetic, two real-world) show that reference guidance consistently strengthens frame-level detection and that the improved frame-level evidence reliably transfers to stronger video-level triage under realistic QA conditions. Code and data are available at: \href{https://github.com/PipiZong/RESP_code.git}{this https URL}.