{
  "id": "2601.21598",
  "title": "Beyond Imitation: Reinforcement Learning for Active Latent Planning",
  "authors": "Zhi Zheng, Wee Sun Lee",
  "first_public": "2026-01-29",
  "venue": "arXiv",
  "arxiv": "2601.21598",
  "paper_url": "https://arxiv.org/abs/2601.21598",
  "code_url": "https://github.com/zz1358m/ATP-Latent-master",
  "lens": [
    "continuous"
  ],
  "representation": [
    "continuous-state"
  ],
  "computation": [
    "recurrent",
    "token-wise"
  ],
  "training": [
    "reinforcement-learning"
  ],
  "questions": [
    "capability",
    "controllability"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "language"
  ],
  "summary": "Uses reinforcement learning to train an active latent-planning process rather than only imitating supervised reasoning traces.",
  "provenance": "Primary-source literature search, 2026-09-04",
  "author_names": [
    "Zhi Zheng",
    "Wee Sun Lee"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2601.21598/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2601-21598",
  "citation_date": "2026-01-29",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2601.21598/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2601.21598/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2601.21598/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2601.21598/citation.csl.json"
}