@article{roverrecursivereasoningovervideoswithvis,
  title = {ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks},
  author = {Philip Schroeder and Ondrej Biza and Thomas Weng and Hongyin Luo and James Glass},
  year = {2025},
  eprint = {2508.01943},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.01943},
}