@article{efficientmultimodalplanningagentforvisua,
  title = {Efficient Multimodal Planning Agent for Visual Question-Answering},
  author = {Zhuo Chen and Xinyu Geng and Xinyu Wang and Yong Jiang and Zhen Zhang and Pengjun Xie and Kewei Tu},
  year = {2026},
  eprint = {2601.20676},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.20676},
}