{
  "id": "2502.05171",
  "title": "Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach",
  "authors": "Jonas Geiping, Sean McLeish, Neel Jain, John Kirchenbauer, Siddharth Singh, Brian R. Bartoldson, Bhavya Kailkhura, Abhinav Bhatele, Tom Goldstein",
  "first_public": "2025-02-07",
  "venue": "arXiv",
  "arxiv": "2502.05171",
  "paper_url": "https://arxiv.org/abs/2502.05171",
  "code_url": "https://github.com/seal-rg/recurrent-pretraining",
  "lens": [
    "recurrent"
  ],
  "representation": [
    "hidden-state"
  ],
  "computation": [
    "recurrent"
  ],
  "training": [
    "pretraining"
  ],
  "questions": [
    "capability",
    "scaling"
  ],
  "evidence": [
    "empirical",
    "scaling"
  ],
  "modality": [
    "language"
  ],
  "summary": "Pretrains a depth-recurrent language model whose computation can be extended at inference time, separating test-time compute from generated token length.",
  "provenance": "Awesome-Latent-CoT",
  "author_names": [
    "Jonas Geiping",
    "Sean McLeish",
    "Neel Jain",
    "John Kirchenbauer",
    "Siddharth Singh",
    "Brian R. Bartoldson",
    "Bhavya Kailkhura",
    "Abhinav Bhatele",
    "Tom Goldstein"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2502.05171/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2502-05171",
  "citation_date": "2025-02-07",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2502.05171/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2502.05171/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2502.05171/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2502.05171/citation.csl.json",
  "publication": {
    "title": "Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach",
    "author_names": [
      "Jonas Geiping",
      "Sean McLeish",
      "Neel Jain",
      "John Kirchenbauer",
      "Siddharth Singh",
      "Brian Bartoldson",
      "Bhavya Kailkhura",
      "Abhinav Bhatele",
      "Tom Goldstein"
    ],
    "year": 2025,
    "type": "paper-conference",
    "container_title": "Advances in Neural Information Processing Systems",
    "publisher": "Curran Associates, Inc.",
    "doi": "10.52202/085713-1380",
    "pages": "41340-41391",
    "volume": "38",
    "url": "https://proceedings.neurips.cc/paper_files/paper/2025/hash/3b01972cf31e6fa0fe29e4b8b5c2a0a1-Abstract-Conference.html",
    "source_url": "https://proceedings.neurips.cc/paper_files/paper/2025/hash/3b01972cf31e6fa0fe29e4b8b5c2a0a1-Abstract-Conference.html",
    "verified_at": "2026-10-18"
  },
  "publication_bibtex_url": "https://latent-implicit-thinking.github.io/papers/2502.05171/publication.bib",
  "publication_csl_url": "https://latent-implicit-thinking.github.io/papers/2502.05171/publication.csl.json",
  "method_comparisons": [
    {
      "title": "Recurrent depth and fixed points",
      "text": "Recurrent depth and fixed-point models repeat computation in different ways. Geiping and colleagues reuse a transformer block, allowing the number of passes to change at inference. The implicit state-space models studied by Schöne and colleagues instead iterate toward a fixed point, with experiments testing when approximate convergence is sufficient. Both add computation without adding a written reasoning trace, but their stopping rules and training costs differ.",
      "source_ids": [
        "2502.05171",
        "2502.07827"
      ],
      "source_urls": [
        "https://proceedings.neurips.cc/paper_files/paper/2025/hash/3b01972cf31e6fa0fe29e4b8b5c2a0a1-Abstract-Conference.html",
        "https://proceedings.mlr.press/v267/schone25a.html"
      ],
      "source_labels": [
        "Recurrent-depth paper",
        "Implicit state-space paper"
      ],
      "topic_id": "recurrent",
      "topic_label": "Recurrent reasoning",
      "topic_url": "https://latent-implicit-thinking.github.io/topics/recurrent-reasoning/"
    }
  ]
}