[
  {
    "id": "lit_2505_13308",
    "type": "article",
    "title": "Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space",
    "author": [
      {
        "literal": "Hengli Li"
      },
      {
        "literal": "Chenxi Li"
      },
      {
        "literal": "Tong Wu"
      },
      {
        "literal": "Xuekai Zhu"
      },
      {
        "literal": "Yuxuan Wang"
      },
      {
        "literal": "Zhaoxin Yu"
      },
      {
        "literal": "Eric Hanchen Jiang"
      },
      {
        "literal": "Song-Chun Zhu"
      },
      {
        "literal": "Zixia Jia"
      },
      {
        "literal": "Ying Nian Wu"
      },
      {
        "literal": "Zilong Zheng"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2025,
          5,
          19
        ]
      ]
    },
    "genre": "Preprint",
    "archive": "arXiv",
    "number": "arXiv:2505.13308",
    "URL": "https://arxiv.org/abs/2505.13308",
    "custom": {
      "record_url": "https://latent-implicit-thinking.github.io/papers/2505.13308/",
      "first_public": "2025-05-19",
      "collection": "core",
      "citation_basis": "ArXiv preprint, using its initial submission date; source URL is not version-pinned."
    }
  }
]
