@article{omagentamultimodalagentframeworkfor,
  title = {OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer},
  author = {Lu Zhang and Tiancheng Zhao and Heting Ying and Yibo Ma and Kyusong Lee},
  year = {2024},
  eprint = {2406.16620},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.16620v3},
}