用大模型模拟真实交易对话，让虚拟交易员更像真人。
TraderTalk: An LLM Behavioural ABM applied to Simulating Human Bilateral Trading Interactions
- 用大模型生成交易对话，驱动虚拟交易员行为
- 复现了真实债券市场的买卖量比，验证了有效性
- 适合金融仿真、行为建模与量化研究者
我们提出一种新型混合方法，将大语言模型（LLM）生成的行为融入基于代理的模型（ABM），用于模拟金融交易中的双边互动。该模型名为TraderTalk。利用在大量人类撰写的文本上训练的LLM，我们捕捉到金融交易中复杂的双向对话特征。将此生成式基于代理模型（GABM）应用于政府债券市场，成功模拟了两个虚拟交易员之间的交易决策。该方法解决了结构难题（如多代理间自然轮次协调）与设计难题（如如何解读LLM输出）。通过非系统性地探索提示工程，提升了代理交互的真实性，避免过度拟合或模型依赖。实验表明，该方法能复现相关资产市场的成交单量比，证明了大模型增强型ABM在金融仿真中的潜力。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。