@article{visraavideobasedspatialreasoningagentfor,
  title = {ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models},
  author = {Tingshu Mou and Jiabo He and Renying Wang and Ce Liu and Hao Yang and Tiehua Zhang and Jingjing Chen and Xingjun Ma},
  year = {2026},
  eprint = {2605.10106},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.10106},
}