PACE

PACE framework applies LLMs to algorithmic parent-order execution in trading

Researchers introduce PACE (Plan-Ahead Controlled Execution), a hierarchical LLM-based framework for parent-order execution in algorithmic trading, decomposing the problem into long-horizon planning and short-horizon execution without requiring market assumptions or task-specific training. Evaluated on Shenzhen Stock Exchange Level-1 data, PACE outperforms TWAP, Almgren-Chriss, and learning-based baselines by up to 0.65 basis points. Behavioral analysis finds LLMs exhibit distinct execution patterns from human traders, including earlier execution and a positive correlation between model confidence and performance. This is the first systematic study extending LLM use in finance from asset selection to order execution.