{
  "abstract": "Multi-agent group-generation systems spend test-time compute uniformly across tasks. We ask whether the agents' own confidence-and-critique trace predicts how hard a task is, which would let the compute be allocated adaptively. Taking as testbed a five-agent orchestrator for Perturb-seq response prediction inspired by CellForge and operated via MassGen, we define four compute-free trace metrics — Agent Confidence Entropy (ACE), Critique Severity Dispersion (CSD), a convergence signal (ΔC), and a Winner Flip Rate (WFR) — and their composite, the Task Difficulty Index (TDI). We pre-register five hypotheses with gates: attainable error on Adamson 2016 (CRISPR interference) and Norman 2019 (CRISPR activation), the Architect agent's backbone-choice entropy, the rank correlation of each TDI component with held-out error, and cross-dataset transfer of a calibrated TDI. The design is 41 held-out K562 tasks (21 Adamson, 15 Norman singletons, 5 Norman doublets) drawn deterministically, a trainer sweep of 27 records per task and three fixed-length agentic lifecycle runs per task, all in one process. The LLM condition is a pinned roster of Anthropic Claude models (Haiku 4.5 for the four proposer roles, Sonnet 5.5 for the Validator) whose served model is recorded and asserted per call; a run with any rule-based fallback step is invalid. Every run records its git revision, resolved configuration, library versions, dataset SHA-256 digests, task plan and label contract. Gate outcomes: 4 of 5 gates pass; H5 fails (0 unevaluated) — the trainer sweep attains the pre-registered error on both screens (H1, H2), the Architect exercises its backbone choice (H3), and the confidence-drop component and the composite rank tasks by held-out error within both screens (H4); the Adamson-calibrated composite does not transfer to Norman at the pre-registered level (H5, ρ = 0.286 against > 0.4). The confidence-entropy point estimates run against the pre-registered direction in both screens (exploratory; no claim is made). The values reported in the v0.5.0 release of this work are superseded in full; the defects behind each are listed in the appendix.",
  "abstract_shown": true,
  "affiliations": [
    "Carnegie Mellon University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Mang-yin Mo",
      "orcid": "0009-0009-5233-3142"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/erteb49863hs6.bib",
  "cited_by": 0,
  "doi": "10.5281/zenodo.23422745",
  "fulltext_url": null,
  "id": "erteb49863hs6",
  "issns": [],
  "landing_url": "https://zenodo.org/records/23422745",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://zenodo.org/api/records/23422745/files/paper.pdf/content",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-16",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/erteb49863hs6.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:19Z",
      "native_id": "23422745",
      "source": "zenodo",
      "url": "https://zenodo.org/records/23422745"
    }
  ],
  "subjects": [],
  "title": "Does Agent Confidence Entropy Predict Task Difficulty? A Pre-registered, Provenance-Complete Test of Agentic Hyperparameter Tuning for Perturb-seq Response Prediction",
  "title_text": "Does Agent Confidence Entropy Predict Task Difficulty? A Pre-registered, Provenance-Complete Test of Agentic Hyperparameter Tuning for Perturb-seq Response Prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:17Z",
  "url": "https://research.draconitic.com/paper/erteb49863hs6",
  "venue": "Zenodo",
  "versions": []
}