发表机构
HKUST(GZ); ZJU; SYSU（香港科技大学（广州）; 浙江大学; 中山大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对算法交易的父订单执行问题，提出分层框架PACE，基于深交所数据验证其性能优于现有方法，表明LLMs可辅助人类交易者执行决策。
AI 中文摘要
父订单执行是算法交易的核心问题，目标是将大额订单拆分为小额订单，同时降低执行成本。现有方法要么依赖实践中可能不成立的预设市场假设，要么需要特定任务训练，限制了对新场景的适应性。为克服这些局限，我们开展了大型语言模型（LLMs）用于父订单执行的首次系统研究，将LLMs在金融领域的应用从“交易什么”拓展至“如何执行”。我们提出PACE（Plan-Ahead Controlled Execution，提前规划的可控执行），这一分层框架将父订单执行分解为长周期规划与短周期执行，无需显式市场假设或特定任务训练。基于深圳证券交易所Level-1数据的实验显示，PACE的表现优于TWAP、Almgren-Chriss及基于学习的基线方法，较最强基线高出0.65个基点。行为分析表明，LLMs的执行决策与人类投资者存在差异：模型更高的置信度对应更优的表现，而非更差的收益，且模型会更早交易，而非拖延至截止时间。这些发现表明，LLMs可在执行决策中为人类交易者提供补充。
英文摘要
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.
