{
  "abstract": "Small language model (SLM) agents need safety controls that track consequences across tool calls with little monitoring overhead. A private read, for example, becomes a leak when a later action sends that data outside the system. We introduce CARB (Conformal Agent Risk Budget), which calibrates when to stop an agent using a ledger of harm incurred before stopping. Under exchangeable episodes, standard conformal risk control bounds this declared loss in expectation over calibration and a future episode. G-CARB selects scorer evidence along observable dependencies from private sources to outgoing actions. The ledger still covers the entire executed history, and computing the gate score requires no additional language-model inference. On AgentDojo replay with two 14B backbones, G-CARB roughly halves scorer-input records at intermediate risk budgets while improving autonomous task completion relative to full-prefix scoring; random context of the same size achieves similar gains. Controlled examples show how retaining the relevant dependency can further avoid stopping benign work.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.05563",
  "author_total": 4,
  "authors": [
    {
      "name": "Zijun Yu"
    },
    {
      "name": "Yu Gu"
    },
    {
      "name": "Vahid Partovi Nia"
    },
    {
      "name": "Masoud Asgharian"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/118d0jxr7w5n7.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.05563",
  "fulltext_url": null,
  "id": "118d0jxr7w5n7",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.05563",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Adversarial Robustness in Machine Learning"
    ]
  ],
  "openalex": "W7220649628",
  "pdf_url": "https://arxiv.org/pdf/2610.05563",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-04",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/118d0jxr7w5n7.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:16Z",
      "native_id": "2610.05563",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.05563"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional Harm",
  "title_text": "G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional Harm",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:16Z",
  "url": "https://research.draconitic.com/paper/118d0jxr7w5n7",
  "venue": "arXiv",
  "versions": []
}