{
  "id": "2607.16972",
  "title": "Training Continuous Chain of Thought Models: A Tale of Two Regimes",
  "authors": "Varun Yerram, He He, Eunsol Choi",
  "first_public": "2026-07-18",
  "venue": "arXiv",
  "arxiv": "2607.16972",
  "paper_url": "https://arxiv.org/abs/2607.16972",
  "code_url": "https://github.com/Varun221/cmtp_research",
  "lens": [
    "continuous",
    "analysis"
  ],
  "representation": [
    "continuous-state"
  ],
  "computation": [
    "token-wise"
  ],
  "training": [
    "supervised"
  ],
  "questions": [
    "capability",
    "efficiency",
    "evaluation",
    "limitations"
  ],
  "evidence": [
    "empirical",
    "boundary"
  ],
  "modality": [
    "language",
    "symbolic"
  ],
  "summary": "Introduces direct latent supervision through averaged trace embeddings and finds that both direct and indirect continuous-CoT training degrade sharply on tasks with substantially longer reasoning traces.",
  "provenance": "Primary-source literature search, 2026-09-05",
  "author_names": [
    "Varun Yerram",
    "He He",
    "Eunsol Choi"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2607.16972/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2607-16972",
  "citation_date": "2026-07-18",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2607.16972/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2607.16972/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2607.16972/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2607.16972/citation.csl.json"
}