{
  "abstract": "Large language model (LLM)-based multi-agent systems face three open challenges in high-stakes decision support: hallucination control in structured output generation, coupling of semantic reasoning with deterministic numerical simulation, and end-to-end auditability of multi-step agentic workflows. We present MacroRisk-Agent , a multi-agent architecture that addresses these challenges in the domain of financial stress testing—a setting that demands strict output validity, reproducibility, and regulatory traceability. MacroRisk-Agent introduces three technical contributions: (1) a retrieval-augmented generation (RAG) pipeline with deterministic validation gates that converts natural-language stress intent into executable, schema-constrained parameter objects, achieving 92.6% validity rate versus 78.4% for RAG-augmented baselines ( $$p<0.001$$ ); (2) a constraint-coupled multi-agent simulation that models endogenous amplification through fire-sale, margin, and liquidity feedback loops, producing a 52% higher systemic-loss estimate than the one-pass configuration under the calibrated experimental setting; and (3) a counterfactual re-simulation framework that validates proposed interventions under identical scenario constraints, achieving 68.6% simulation-defined top-1 decision success rate. We evaluate MacroRisk-Agent as a proof-of-concept on public financial datasets (FRED, Yahoo Finance), a library of 150 curated crisis events, and 10 synthetic institutional portfolios; reported improvements are statistically significant across scenario validity, propagation modeling, and intervention quality within this synthetic evaluation environment . We position the framework as a proposed architecture—rather than an empirically validated, deployment-ready system—for building hallucination-controlled, provenance-tracked LLM-agent pipelines that are designed to improve auditability in high-stakes settings; validation on real institutional data is left to future work.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "name": "Yan Liu"
    },
    {
      "name": "Junyi Shangguan"
    },
    {
      "name": "Qianyi Wang"
    },
    {
      "name": "Shangfei Xu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/c2bw7qd50vzjz.bib",
  "cited_by": 0,
  "doi": "10.1038/s41598-026-73453-3",
  "fulltext_url": null,
  "id": "c2bw7qd50vzjz",
  "issns": [
    "2045-2322"
  ],
  "landing_url": "https://www.nature.com/articles/s41598-026-73453-3",
  "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",
      "2003|Banking stability, regulation, efficiency"
    ]
  ],
  "openalex": "W7220916758",
  "pdf_url": "https://www.nature.com/articles/s41598-026-73453-3_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-08",
  "publisher": "Springer Science and Business Media LLC",
  "ris": "https://research.draconitic.com/paper/c2bw7qd50vzjz.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:24Z",
      "native_id": "10.1038/s41598-026-73453-3",
      "source": "crossref",
      "url": "https://www.nature.com/articles/s41598-026-73453-3"
    }
  ],
  "subjects": [],
  "title": "MacroRisk-agent: a retrieval-augmented multi-agent framework with deterministic validation gates for auditable stress testing",
  "title_text": "MacroRisk-agent: a retrieval-augmented multi-agent framework with deterministic validation gates for auditable stress testing",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:24Z",
  "url": "https://research.draconitic.com/paper/c2bw7qd50vzjz",
  "venue": "Scientific Reports",
  "versions": []
}