Automate Strategy Finding with LLM in Quant Investment

TL;DR

This paper introduces a three-stage framework using Large Language Models within a multi-agent system to automate and improve quantitative trading strategy development, demonstrating superior performance in Chinese and US markets.

Contribution

It presents a novel, scalable architecture that combines prompt-engineered LLMs, multimodal evaluation, and dynamic optimization for financial signal extraction and portfolio management.

Findings

Achieved 53.17% cumulative return on SSE50 from Jan 2023 to Jan 2024.

Outperformed established benchmarks in Chinese and US markets.

Demonstrated robust risk-adjusted performance and downside protection.

Abstract

We present a novel three-stage framework leveraging Large Language Models (LLMs) within a risk-aware multi-agent system for automate strategy finding in quantitative finance. Our approach addresses the brittleness of traditional deep learning models in financial applications by: employing prompt-engineered LLMs to generate executable alpha factor candidates across diverse financial data, implementing multimodal agent-based evaluation that filters factors based on market status, predictive quality while maintaining category balance, and deploying dynamic weight optimization that adapts to market conditions. Experimental results demonstrate the robust performance of the strategy in Chinese & US market regimes compared to established benchmarks. Our work extends LLMs capabilities to quantitative trading, providing a scalable architecture for financial signal extraction and portfolio construction. The overall framework significantly outperforms all benchmarks with 53.17% cumulative return on SSE50 (Jan 2023 to Jan 2024), demonstrating superior risk-adjusted performance and downside protection on the market.