Trading Strategy Optimization via Textual Gradient

2026-10-02

AI Summary

This study addresses the underutilization of empirical experience and poor intertemporal robustness in quantitative strategy optimization by proposing the TradeGrad framework. This method leverages large language models to estimate textual gradients, integrating cumulative experience-guided optimization with a multi-scale revision mechanism to search for robust trading programs. Furthermore, it introduces a Cross-Period Robust Objective (CPRO) that reinforces strategy performance during adverse historical periods to enhance temporal stability. Experimental results demonstrate that the proposed framework achieves state-of-the-art in-sample and out-of-sample performance across both Chinese and U.S. markets. Notably, the cross-sectional strategy applied to China's A-share market yields an annualized return of 27.99%, significantly outperforming existing baselines.

Abstract

Quantitative trading strategy design aims to discover trading programs from historical data that remain effective in future markets, which can be viewed as a black-box program optimization problem. LLM-based textual gradients offer a promising approach by providing explicit optimization directions for iterative strategy refinement. However, directly applying textual gradients faces two challenges: (1) optimization is myopic, underutilizing experience from previous evaluations; and (2) aggregate backtest feedback overlooks temporal robustness, potentially favoring strategies that perform well only in specific market periods. To address these challenges, we propose TradeGrad, an experience-guided textual-gradient framework for robust trading strategy optimization. TradeGrad leverages accumulated optimization experience to estimate textual gradients and employs multi-scale revisions for both strategy exploration and refinement. It further introduces the Cross-Period Robust Objective (CPRO), which emphasizes performance in unfavorable historical periods to promote temporal robustness. Experiments on cross-sectional and time-series strategy design in Chinese A-share and U.S. equity markets show that TradeGrad achieves the best in-sample and out-of-sample performance across all four settings. Notably, its Chinese cross-sectional strategy achieves 27.99% annualized return, 12.19% maximum drawdown, and a Sharpe ratio of 1.63, approximately 68% higher than the CSI 300 benchmark. Further analyses validate the proposed components and show consistent improvements in both in-sample and out-of-sample performance throughout optimization. The code is available at https://github.com/transcend-0/TradeGrad.

Problem

• Quantitative Trading
• Strategy Optimization
• Textual Gradient
• Temporal Robustness
• Black-box Optimization

Innovation

• Textual Gradient
• Trading Strategy Optimization
• Large Language Models
• Cross-Period Robust Objective
• Experience-Guided Framework