Reproduce “Agent4Crypto: A Dual-Reflective and Market-Feedback-Aligned LLM-Based Multi-Agent System for Cryptocurrency 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
Guangyan Gan, Jiahao Li, Jiashun Wang, Lin William Cong
Agent4Crypto combines proposals from three LLM traders—Aggressive, Neutral, and Conservative—with weights learned by a PPO gate using portfolio returns and hypothetical scores from Counterfactual Contribution Memory. Financial ReasoningBank lessons inform trader prompts. Across BTC, ETH, and XRP test windows, it reports the highest total returns and Sharpe ratios among methods, although ETH and XRP returns remain negative.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.