{
  "abstract": "Bitcoin perpetual futures trade continuously with shallow liquidity and high price impact, making them prone to millisecond-scale flash crashes. Agent-based limit order book simulators are a natural tool for studying such events, but their behavioral parameters are usually hand-crafted or require full order book histories that are rarely available at scale. We propose a four-stage pipeline that constructs a reproducible 100 ms BTCUSDT flash-crash event panel from 66 detected events, elicits behavioral priors for four agent archetypes using an offline large language model conditioned on empirical microstructure anchors, instantiates a heterogeneous limit order book simulator with the validated priors, and applies causal discovery plus counterfactual analysis to the resulting synthetic panel. Across 500 simulation runs, LLM-elicited priors produce a crash rate of 0.176 versus 0.008 under uninformative uniform priors and generate heav- ier return tails. In the frozen counterfactual analysis, reducing leverage amplification by one within-sample standard deviation lowers the predicted crash rate from 0.176 to 0.136, whereas reducing directional pressure yields only a marginal change. These find- ings suggest that empirically anchored LLM elicitation can improve simulator fidelity and help identify plausible crash-amplification mechanisms in a controlled synthetic environment",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.03660",
  "author_total": 6,
  "authors": [
    {
      "name": "Tran Phuong Linh Pham"
    },
    {
      "name": "Thi Minh Phuong Ngo"
    },
    {
      "name": "Phuong Thao Nguyen"
    },
    {
      "name": "Quang Minh Nguyen"
    },
    {
      "name": "Thai Hoa Ngo"
    },
    {
      "name": "Trong Nghia Nguyen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8pftqtpydms04.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.03660",
  "fulltext_url": null,
  "id": "8pftqtpydms04",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.03660",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "q-fin.TR"
    ],
    [
      "arxiv",
      "stat.AP"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.03660",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8pftqtpydms04.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T15:21:34Z",
      "native_id": "2611.03660",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.03660"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.AP",
      "subfield": "statistics"
    }
  ],
  "title": "Behavioral Prior Elicitation via LLM for Heterogeneous-Agent Bitcoin Flash-Crash Simulation",
  "title_text": "Behavioral Prior Elicitation via LLM for Heterogeneous-Agent Bitcoin Flash-Crash Simulation",
  "type": "preprint",
  "updated_at": "2026-11-05T15:20:44Z",
  "url": "https://research.draconitic.com/paper/8pftqtpydms04",
  "venue": "arXiv",
  "versions": []
}