{
  "id": "2505.13308",
  "title": "Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space",
  "authors": "Hengli Li, Chenxi Li, Tong Wu, Xuekai Zhu, Yuxuan Wang, Zhaoxin Yu, Eric Hanchen Jiang, Song-Chun Zhu, Zixia Jia, Ying Nian Wu, Zilong Zheng",
  "first_public": "2025-05-19",
  "venue": "arXiv",
  "arxiv": "2505.13308",
  "paper_url": "https://arxiv.org/abs/2505.13308",
  "lens": [
    "continuous"
  ],
  "representation": [
    "continuous-state"
  ],
  "computation": [
    "search"
  ],
  "training": [
    "test-time-optimization"
  ],
  "questions": [
    "capability",
    "controllability"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "language",
    "symbolic"
  ],
  "summary": "Optimizes latent states for individual problems at test time using policy gradients rather than searching over written reasoning traces.",
  "provenance": "Primary-source literature search, 2026-09-04",
  "author_names": [
    "Hengli Li",
    "Chenxi Li",
    "Tong Wu",
    "Xuekai Zhu",
    "Yuxuan Wang",
    "Zhaoxin Yu",
    "Eric Hanchen Jiang",
    "Song-Chun Zhu",
    "Zixia Jia",
    "Ying Nian Wu",
    "Zilong Zheng"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2505.13308/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2505-13308",
  "citation_date": "2025-05-19",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2505.13308/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2505.13308/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2505.13308/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2505.13308/citation.csl.json"
}