跳至正文
返回文库全部文档

用于零样本加密货币交易的反思式 LLM 智能体

文章 arXiv papers · 作者: Yuan Li et al.
阅读原文

总结

本文介绍 CryptoTrade，这是一种基于大型语言模型构建的加密货币交易智能体。其方法结合链上信息（作者认为这类信息透明且不可篡改）和新闻等链下信号，后者可以提供及时背景。反思机制会回顾早前决策的结果，为智能体每日交易决策提供参考，使其能够纳入交易反馈，而不只依赖传统时间序列基准。

作者报告了涵盖多种加密货币和市场状况的实验，并声称 CryptoTrade 的收益高于传统策略和时间序列基准。所提供的描述没有指出资产、评估时期、收益指标、交易成本、风险调整后结果，或防止数据泄漏的措施。因此，绩效说法应视为对所报告实验的概述，而非该智能体能够推广到实盘交易或其他市场环境的证据。

核心观点

  • CryptoTrade 将链上数据与新闻等链下信息结合起来。
  • 反思机制利用早前交易结果指导后续每日决策。
  • 作者报告了涵盖多种加密货币和市场状况的实验。
  • 作者声称其收益高于传统策略和时间序列基准。
  • 所提供的描述缺少评估细节，无法据此判断风险及其对实盘市场的适用性。

标签

加密资产机器学习链上数据市场情绪
全文
# A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading


# A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading









The utilization of Large Language Models (LLMs) in financial trading has primarily been concentrated within the stock market, aiding in economic and financial decisions. Yet, the unique opportunities presented by the cryptocurrency market, noted for its on-chain data's transparency and the critical influence of off-chain signals like news, remain largely untapped by LLMs. This work aims to bridge the gap by developing an LLM-based trading agent, CryptoTrade, which uniquely combines the analysis of on-chain and off-chain data. This approach leverages the transparency and immutability of on-chain data, as well as the timeliness and influence of off-chain signals, providing a comprehensive overview of the cryptocurrency market. CryptoTrade incorporates a reflective mechanism specifically engineered to refine its daily trading decisions by analyzing the outcomes of prior trading decisions. This research makes two significant contributions. Firstly, it broadens the applicability of LLMs to the domain of cryptocurrency trading. Secondly, it establishes a benchmark for cryptocurrency trading strategies. Through extensive experiments, CryptoTrade has demonstrated superior performance in maximizing returns compared to traditional trading strategies and time-series baselines across various cryptocurrencies and market conditions. Our code and data are available at https://anonymous.4open.science/r/CryptoTrade-Public-92FC/.

在遵守原作品许可的前提下，附作者信息全文展示。 许可协议: abstract CC0

此摘要由 Stratmill 研究智能体根据原文撰写，并非原文副本。