{
  "id": "2609.39740",
  "title": "LatentHarness: Learning Latent Actions for Memory and Reasoning via Counterfactual Policy Distillation",
  "authors": "Xiaoqiang Wang, Suyuchen Wang, Bang Liu",
  "first_public": "2026-09-30",
  "added_at": "2026-10-18",
  "venue": "arXiv",
  "arxiv": "2609.39740",
  "paper_url": "https://arxiv.org/abs/2609.39740",
  "lens": [
    "continuous",
    "recurrent"
  ],
  "representation": [
    "continuous-state",
    "cache-memory"
  ],
  "computation": [
    "stateful",
    "recurrent"
  ],
  "training": [
    "distillation"
  ],
  "questions": [
    "capability",
    "efficiency",
    "architecture"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "language"
  ],
  "summary": "Learns when to perform another internal reasoning step, recall stored evidence or intermediate states, or emit a token. Trains these choices by branching over alternative actions and measuring their effects on the next emitted token.",
  "provenance": "Primary-source literature search, 2026-10-18",
  "author_names": [
    "Xiaoqiang Wang",
    "Suyuchen Wang",
    "Bang Liu"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2609.39740/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2609-39740",
  "citation_date": "2026-09-30",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2609.39740/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2609.39740/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2609.39740/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2609.39740/citation.csl.json"
}