@article{hybridadvantageestimationwithunifiedcrit,
  title = {Hybrid Advantage Estimation with Unified Critic for VLM Agentic Reinforcement Learning},
  author = {Wenxuan Zhang and Yuhui Wang and Donggang Jia and Xiaoqian Shen and Jian Ding and Ivan Viola and Jürgen Schmidhuber and Mohamed Elhoseiny},
  year = {2026},
  eprint = {2607.23605},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.23605},
}