@misc{lit_2505_13308,
  title = { {Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space} },
  author = {Hengli Li and Chenxi Li and Tong Wu and Xuekai Zhu and Yuxuan Wang and Zhaoxin Yu and Eric Hanchen Jiang and Song-Chun Zhu and Zixia Jia and Ying Nian Wu and Zilong Zheng},
  year = {2025},
  note = {arXiv preprint},
  eprint = {2505.13308},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.13308}
}
