{
  "id": "2508.03440",
  "title": "LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking",
  "authors": "Junhong Wu, Jinliang Lu, Zixuan Ren, Gangqiang Hu, Zhi Wu, Dai Dai, Hua Wu",
  "first_public": "2025-08-05",
  "added_at": "2026-10-18",
  "venue": "arXiv",
  "arxiv": "2508.03440",
  "paper_url": "https://arxiv.org/abs/2508.03440",
  "lens": [
    "analysis",
    "continuous"
  ],
  "representation": [
    "continuous-state"
  ],
  "computation": [
    "token-wise"
  ],
  "training": [
    "analysis-only",
    "inference-only"
  ],
  "questions": [
    "interpretability",
    "limitations",
    "capability"
  ],
  "evidence": [
    "probing",
    "empirical",
    "boundary"
  ],
  "modality": [
    "language",
    "symbolic"
  ],
  "summary": "Probes soft-token reasoning and finds that tested models often follow the highest-probability component rather than exploring several paths at once. Introduces stochastic soft thinking, including Gumbel-Softmax sampling, to reduce this greedy behavior.",
  "provenance": "Awesome-Latent-CoT; primary sources checked 2026-10-18",
  "author_names": [
    "Junhong Wu",
    "Jinliang Lu",
    "Zixuan Ren",
    "Gangqiang Hu",
    "Zhi Wu",
    "Dai Dai",
    "Hua Wu"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2508.03440/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2508-03440",
  "citation_date": "2025-08-05",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2508.03440/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2508.03440/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2508.03440/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2508.03440/citation.csl.json"
}