Reproduce “EVOQUANT: Self-Evolving Verifier-Guided Strategy Optimization for Robust Quantitative Trading” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jie Mao, Changlun Li, Xiang Li, Qiqi Duan, Jinhui Yuan, Xiang Liu, Yuyu Luo, Jing Tang and 1 more
EVOQUANT improves user-provided trading strategies by having a language model propose bounded edits and using verification and promotion gates to decide whether to adopt them. In historical A-share backtests, the equal-weighted Volume Breakout portfolio’s test Sharpe rose from −0.493 to 0.489, while maximum drawdown worsened from 4.81% to 6.62%. These daily-bar results do not establish live-trading performance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.