TraderTalk: An LLM Behavioural ABM applied to Simulating Human Bilateral Trading Interactions

ArXiv ID: 2410.21280 “View on arXiv”

Authors: Unknown

Abstract

We introduce a novel hybrid approach that augments Agent-Based Models (ABMs) with behaviors generated by Large Language Models (LLMs) to simulate human trading interactions. We call our model TraderTalk. Leveraging LLMs trained on extensive human-authored text, we capture detailed and nuanced representations of bilateral conversations in financial trading. Applying this Generative Agent-Based Model (GABM) to government bond markets, we replicate trading decisions between two stylised virtual humans. Our method addresses both structural challenges, such as coordinating turn-taking between realistic LLM-based agents, and design challenges, including the interpretation of LLM outputs by the agent model. By exploring prompt design opportunistically rather than systematically, we enhance the realism of agent interactions without exhaustive overfitting or model reliance. Our approach successfully replicates trade-to-order volume ratios observed in related asset markets, demonstrating the potential of LLM-augmented ABMs in financial simulations

Keywords: Agent-Based Models, Large Language Models, Generative Agent-Based Model, financial simulation, LLM, Government Bonds

Complexity vs Empirical Score

  • Math Complexity: 4.0/10
  • Empirical Rigor: 3.0/10
  • Quadrant: Philosophers
  • Why: The paper is conceptually focused on a novel hybrid (LLM + ABM) framework for simulating trading interactions, with minimal advanced mathematics (primarily descriptive statistics and simple ratios). Empirically, it presents a proof-of-concept with limited backtesting (300 simulations) and no reported data processing or implementation details, relying instead on opportunistic prompt design.
  flowchart TD
    A["Research Goal: Simulate Human Bilateral Trading"] --> B["Methodology: TraderTalk GABM"]
    B --> C["Data: LLM trained on<br>Human-authored Text"]
    C --> D["Computational Process:<br>LLM-generated Behaviors"]
    D --> E["Simulation: Government Bond<br>Bilateral Trading"]
    E --> F["Outcome: Replicated<br>Trade-to-Order Volume Ratios"]