大型语言模型能否执行母订单？

摘要

母单执行是算法交易中的核心问题，其目标是将大额订单拆分为小额订单，同时降低执行成本。现有方法要么依赖事先设定的市场假设，而这类假设在实践中可能不成立；要么需要针对特定任务的训练，从而限制了其适应新场景的能力。为克服上述局限，我们首次对大型语言模型（LLM）用于母单执行进行了系统性研究。这将LLM在金融领域的应用从"交易什么"拓展到"如何执行"。我们提出PACE（Plan-Ahead Controlled Execution，前瞻规划受控执行）框架，这是一个分层框架，将母单执行分解为长视野规划与短视野执行两个环节，既不需要显式的市场假设，也无需针对特定任务的训练。在深圳证券交易所Level-1数据上的实验表明，PACE优于TWAP、Almgren-Chriss及基于学习的基线方法，比最强基线高出0.65个基点。行为分析揭示，LLM在执行决策上与人类投资者存在差异：较高的模型置信度预示着更好的绩效而非更差的收益，且模型倾向于提前交易而非拖延至截止时间。这些发现表明，LLM能够在执行决策中为人类交易员提供补充。

English

Parent-order execution is a core problem in algorithmic trading, where the goal is to split a large order into smaller orders while reducing execution costs. Existing approaches either rely on pre-specified market assumptions that may not hold in practice, or require task-specific training that limits adaptability to new settings. To overcome these limitations, we present the first systematic study of large language models (LLMs) for parent-order execution. This extends the use of LLMs in finance from what to trade to how to execute. We propose PACE (Plan-Ahead Controlled Execution), a hierarchical framework that decomposes parent-order execution into long-horizon planning and short-horizon execution, requiring neither explicit market assumptions nor task-specific training. Experiments on Shenzhen Stock Exchange Level-1 data show that PACE outperforms TWAP, Almgren-Chriss, and learning-based baselines, exceeding the strongest baseline by 0.65 bps. Behavioral analysis reveals that LLMs make execution decisions differently from human investors: higher model confidence predicts better performance rather than worse returns, and the model trades earlier rather than procrastinating toward the deadline. These findings suggest that LLMs can complement human traders in execution decisions.