Spatio-temporal reasoning is a core capability for Multimodal Large Language Models (MLLMs) operating in the real world. As such, evaluating it precisely has become an essential challenge. However, existing spatio-temporal reasoning benchmark datasets primarily rely on static image sets or passively curated video data, which limits the evaluation of fine-grained reasoning capabilities. In this paper, we introduce VGenST-Bench, a video benchmark that employs generative models to actively synthesize highly controlled and diverse evaluation scenarios. To construct VGenST-Bench, we propose a multi-agent pipeline incorporating a human quality control stage, ensuring the quality of all generated videos and QA pairs. We establish a comprehensive 3x2x2 video taxonomy, encompassing Spatial Scale, Perspective, and Scene Dynamics to span diverse scenarios. Furthermore, we design a hierarchical task suite that decouples low-level visual perception from high-level spatio-temporal reasoning. By shifting the paradigm from passive curation to active synthesis, VGenST-Bench enables fine-grained diagnosis of spatio-temporal understanding in MLLMs.
@article{arxiv.2605.22570,
title = {VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis},
author = {Jinho Park and Youbin Kim and Hogun Park and Eunbyung Park},
journal= {arXiv preprint arXiv:2605.22570},
year = {2026}
}
Comments
82 pages, 91 figures (7 in main paper, 84 in appendix). Project page: https://zinosii.github.io/VGenST-Bench/