# Behavioral Prior Elicitation via LLM for Heterogeneous-Agent Bitcoin Flash-Crash Simulation

DevFeed: [Behavioral Prior Elicitation via LLM for Heterogeneous-Agent Bitcoin Flash-Crash Simulation](<https://devfeed.tech/articles/behavioral-prior-elicitation-via-llm-for-heterogeneous-agent-bitcoin-flash-crash-simulation-117350.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.03660>)

Author: Tran Phuong Linh Pham, Thi Minh Phuong Ngo, Phuong Thao Nguyen, Quang Minh Nguyen, Thai Hoa Ngo, Trong Nghia Nguyen

Published: 2026-11-04T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Simulation](<https://devfeed.tech/topics/simulation.md>)

Tags: [bitcoin](<https://devfeed.tech/tags/bitcoin.md>), [counterfactual-analysis](<https://devfeed.tech/tags/counterfactual-analysis.md>), [crash](<https://devfeed.tech/tags/crash.md>), [crash-simulation](<https://devfeed.tech/tags/crash-simulation.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [flash](<https://devfeed.tech/tags/flash.md>), [large](<https://devfeed.tech/tags/large.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [leverage](<https://devfeed.tech/tags/leverage.md>), [limit-order-book](<https://devfeed.tech/tags/limit-order-book.md>), [llm](<https://devfeed.tech/tags/llm.md>), [q-fin-tr](<https://devfeed.tech/tags/q-fin-tr.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [stat-ap](<https://devfeed.tech/tags/stat-ap.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [tails](<https://devfeed.tech/tags/tails.md>)

## AI overview

The study uses an offline LLM, conditioned on empirical microstructure anchors, to elicit behavioral priors for four agent types in a heterogeneous BTCUSDT limit order book simulator. Its four-stage pipeline builds a 100 ms event panel from 66 detected flash crashes, validates the priors, then uses synthetic simulations for causal discovery and counterfactual analysis. Across 500 runs, LLM-elicited priors yielded a 0.176 crash rate versus 0.008 with uniform priors and produced heavier return tails. In the frozen counterfactual, lowering leverage amplification by one within-sample standard deviation reduced predicted crash rate to 0.136; lowering directional pressure had only a marginal effect. The findings concern a controlled synthetic environment.

## Source excerpt

arXiv:2611.03660v1 Announce Type: cross 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