# Evaluating VLMs for Autonomous Agent-Driven Geometry Clipping Detection in Video Game QA

arXiv: https://arxiv.org/abs/2607.25921 · HTML: https://mlsanity.com/paper/2607.25921/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 11 of its 13 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 11 of 11)

- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos](https://mlsanity.com/paper/2412.01800/) (2024)
- [Using Reinforcement Learning for Load Testing of Video Games](https://mlsanity.com/paper/2201.06865/) (2022)
- [VideoGameQA-Bench: Evaluating Vision-Language Models for Video Game Quality Assurance](https://mlsanity.com/paper/2505.15952/) (2025)
- [Robust Imitation Learning for Automated Game Testing](https://mlsanity.com/paper/2401.04572/) (2024)
- [World of Bugs: A Platform for Automated Bug Detection in 3D Video Games](https://mlsanity.com/paper/2206.11037/) (2022)
- [Go-Explore Complex 3D Game Environments for Automated Reachability Testing](https://mlsanity.com/paper/2209.00570/) (2022)
- [Bayesian Optimization-based Search for Agent Control in Automated Game Testing](https://mlsanity.com/paper/2508.13121/) (2025)
- [RefGlitch-Bench: A Benchmark for Reference-based Gameplay Glitch Detection with Vision-Language Models](https://mlsanity.com/paper/2604.11082/) (2026)
- [Behavioural Cloning in VizDoom](https://mlsanity.com/paper/2401.03993/) (2024)
- [Learning Representations in Video Game Agents with Supervised Contrastive Imitation Learning](https://mlsanity.com/paper/2509.11880/) (2025)

## Abstract (arXiv)

In this work, we study the use of Vision-Language Models (VLMs) for anomaly detection in an agent-driven game Quality Assurance (QA) pipeline focusing on geometry clipping. In this evaluation, a custom exploration agent navigates a game level to collect visual observations, while the automatic annotation pipeline provides frame-level clipping labels. This setup allows us to evaluate recent VLMs on a controlled anomaly detection task without manual annotation. We benchmark six recent VLMs (Gemini, GPT, Qwen, Gemma, Llama, and Ministral) under a zero-shot prompting setting and analyse their sensitivity to four prompt variants. Our results show that while the VLMs can capture visual cues associated with geometry clipping, they all produce substantial false positives on visually ambiguous frames such as near-contact geometry and partial occlusions. Gemini-3.1-Flash achieves the best overall accuracy and is the most robust to prompt variation, while open-source models exhibit large precision--recall swings depending on the prompt design. These findings suggest that current VLMs are best suited as high-recall candidate filters within multi-stage QA pipelines rather than as standalone bug detectors.