{
  "id": "2606.13106",
  "title": "Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning",
  "authors": "Jiayu Yang, Chao Chen, Shengen Wu, Yinhong Liu, Yuxuan Fan, Lujundong Li, Songning Lai, Chengwei Qin, Zhijiang Guo",
  "first_public": "2026-06-11",
  "venue": "arXiv",
  "arxiv": "2606.13106",
  "paper_url": "https://arxiv.org/abs/2606.13106",
  "lens": [
    "continuous",
    "recurrent",
    "analysis"
  ],
  "representation": [
    "continuous-state",
    "text-latent-hybrid"
  ],
  "computation": [
    "recurrent",
    "token-wise"
  ],
  "training": [
    "reinforcement-learning",
    "curriculum"
  ],
  "questions": [
    "capability",
    "interpretability",
    "controllability"
  ],
  "evidence": [
    "empirical",
    "mechanistic"
  ],
  "modality": [
    "language"
  ],
  "summary": "Trains switchable hidden-state recurrence with on-policy reinforcement learning and analyzes how the internal loop contributes to reasoning.",
  "provenance": "Primary-source literature search, 2026-09-04",
  "author_names": [
    "Jiayu Yang",
    "Chao Chen",
    "Shengen Wu",
    "Yinhong Liu",
    "Yuxuan Fan",
    "Lujundong Li",
    "Songning Lai",
    "Chengwei Qin",
    "Zhijiang Guo"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2606.13106/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2606-13106",
  "citation_date": "2026-06-11",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2606.13106/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2606.13106/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2606.13106/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2606.13106/citation.csl.json"
}