Shifting Power: Leveraging LLMs to Simulate Human Aversion in ABMs of Bilateral Financial Exchanges, A bond market study

ArXiv ID: 2503.00320 “View on arXiv”

Authors: Unknown

Abstract

Bilateral markets, such as those for government bonds, involve decentralized and opaque transactions between market makers (MMs) and clients, posing significant challenges for traditional modeling approaches. To address these complexities, we introduce TRIBE an agent-based model augmented with a large language model (LLM) to simulate human-like decision-making in trading environments. TRIBE leverages publicly available data and stylized facts to capture realistic trading dynamics, integrating human biases like risk aversion and ambiguity sensitivity into the decision-making processes of agents. Our research yields three key contributions: first, we demonstrate that integrating LLMs into agent-based models to enhance client agency is feasible and enriches the simulation of agent behaviors in complex markets; second, we find that even slight trade aversion encoded within the LLM leads to a complete cessation of trading activity, highlighting the sensitivity of market dynamics to agents’ risk profiles; third, we show that incorporating human-like variability shifts power dynamics towards clients and can disproportionately affect the entire system, often resulting in systemic agent collapse across simulations. These findings underscore the emergent properties that arise when introducing stochastic, human-like decision processes, revealing new system behaviors that enhance the realism and complexity of artificial societies.

Keywords: Agent-based Modeling, LLM (Large Language Model), Market Making, Bilateral Markets, Simulation

Complexity vs Empirical Score

• Math Complexity: 4.0/10
• Empirical Rigor: 6.5/10
• Quadrant: Street Traders
• Why: The paper’s math complexity is moderate, relying on established agent-based modeling and statistical concepts without dense derivations, while empirical rigor is relatively high due to its use of publicly available data, simulation frameworks, and emphasis on implementation-heavy backtesting in a specific bond market context.

  flowchart TD
    A["Research Goal<br>Simulate human aversion in<br>bilateral financial markets"] --> B["Methodology<br>TRIBE: ABM + LLM Agent"]

    B --> C["Data & Inputs<br>Market Stylized Facts<br>Risk/Ambiguity Parameters"]
    
    C --> D["Computational Process<br>1. MM & Client Agents<br>2. LLM-Driven Decisions<br>3. Bilateral Matching"]

    D --> E["Key Finding 1<br>Feasibility: LLM enhances<br>client agency & realism"]

    D --> F["Key Finding 2<br>Sensitivity: Slight aversion<br>causes total trade cessation"]

    D --> G["Key Finding 3<br>Power Shift: Human variability<br>shifts power to clients &<br>risks systemic collapse"]