arXiv · 2025 · Preprint

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space

Hengli Li, Chenxi Li, Tong Wu, Xuekai Zhu, Yuxuan Wang, Zhaoxin Yu, Eric Jiang, Song-Chun Zhu, Zixia Jia, Ying-Nian Wu, Zilong Zheng

Date
2025-05-19
Citations
38
arXiv
2505.13308
Cite
@misc{li2025seek,
  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 Jiang and Song-Chun Zhu and Zixia Jia and Ying-Nian Wu and Zilong Zheng},
  year = {2025},
  eprint = {2505.13308},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.13308},
}