QuantEvolve: Automating Quantitative Strategy Discovery through Multi-Agent Evolutionary Framework

TL;DR

QuantEvolve addresses the challenge of automated, diverse quantitative strategy discovery in dynamic markets by integrating a quality-diversity, feature-map framework with a hypothesis-driven multi-agent search. The system preserves behavioral diversity across investor-relevant dimensions, while a population of agents systematically generates and tests hypotheses to refine strategies, guided by an Evolutionary Database and island migrations. Empirical results in equities and futures show the evolved strategies outperform conventional baselines on risk-adjusted and relative metrics, demonstrating robustness across regimes. By releasing a dataset of evolved strategies, QuantEvolve advances automated quantitative research and supports personalized asset management at scale.

Abstract

Automating quantitative trading strategy development in dynamic markets is challenging, especially with increasing demand for personalized investment solutions. Existing methods often fail to explore the vast strategy space while preserving the diversity essential for robust performance across changing market conditions. We present QuantEvolve, an evolutionary framework that combines quality-diversity optimization with hypothesis-driven strategy generation. QuantEvolve employs a feature map aligned with investor preferences, such as strategy type, risk profile, turnover, and return characteristics, to maintain a diverse set of effective strategies. It also integrates a hypothesis-driven multi-agent system to systematically explore the strategy space through iterative generation and evaluation. This approach produces diverse, sophisticated strategies that adapt to both market regime shifts and individual investment needs. Empirical results show that QuantEvolve outperforms conventional baselines, validating its effectiveness. We release a dataset of evolved strategies to support future research.

Figures (13)

• Figure 1: Architecture of the proposed QuantEvolve framework.
• Figure 2: Multi-agent evolution architecture.
• Figure 3: Exchange of superior strategies across islands.
• Figure 4: Initialization of QuantEvolve.
• Figure 5: Evolution of the feature map across max drawdown and category dimensions, measured by Sharpe ratio.