{
  "id": 15230,
  "url": "https://arxiv.org/abs/2607.28317v1",
  "title": "One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence",
  "summary": "A single human must audit $N$ LLM agents under a budget of $B \\ll N$ audits per round, guided by self-reported confidence that may be adversarially miscalibrated and by correlated errors. We model this as budgeted noisy inspection over a two-level Gaussian copula and locate the miscalibration threshold $δ^*$ past which confidence-ranked auditing is \\emph{worse} than random. Two a-priori expectations reverse: $δ^*$ \\emph{rises} as the budget shrinks, and cross-family correlation is not low---shar",
  "authors": "Cesare Zavattari, Alessandro Tommasi, Giuseppe Prencipe",
  "category": "research",
  "topics": "agents-autonomy,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-30T14:52:36.000Z",
  "fetched_at": "2026-07-31T05:10:57.675Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/15230",
  "original_url": "https://arxiv.org/abs/2607.28317v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}