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

2025-03-01

AI Summary

Traditional financial market models fail to capture human behavioral aversion—such as risk aversion and ambiguity sensitivity—as well as the decentralized, opaque trading characteristics prevalent in bilateral markets (e.g., government bond markets). Method: We propose TRIBE, a novel multi-agent framework embedding the Llama-3 large language model (LLM) into agent-based modeling—marking the first LLM-driven client-agent architecture. TRIBE integrates empirically grounded behavioral rules and is calibrated using real-market transaction data. Contribution/Results: Our simulations reveal that infinitesimal aversion parameters can trigger systemic market freezes; behavioral heterogeneity systematically inverts trading power hierarchies, precipitating client-led cascading failures; and LLM-enhanced agents significantly improve behavioral fidelity. Quantitatively, we identify a sharp aversion threshold effect and document high-frequency, system-wide collapse events—demonstrating how micro-level psychological traits propagate to macro-level instability.

Technology Category

• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Simulate human-like decision-making in bilateral financial markets.
• Integrate human biases like risk aversion into trading models.
• Explore effects of human-like variability on market dynamics.

Innovation

• LLM-augmented agent-based model for trading simulations
• Integration of human biases into agent decision-making
• Simulation of systemic effects from client power shifts