跳至正文
返回文库全部文档

区分LLM加密货币交易中的事实与主观推理

文章 arXiv papers · 作者: Qian Wang et al.
阅读原文

总结

本文探讨为何能力更强的大语言模型有时在加密货币交易中的表现不如较弱模型。文中认为，部分原因是较强模型倾向于优先采用事实信息，而非主观解读。提出的FS-ReasoningAgent框架将推理拆分为事实和主观两部分，使交易决策能够结合这两类输入。

报告的实验显示，BTC、ETH和SOL的收益有所提升，增幅分别为7%、2%和10%。消融研究报告称，主观新闻在牛市中表现更好，而事实信息在熊市中表现更好。这些结果表明，两种推理模式的相对价值可能取决于市场状况。本文未说明完整实验设置、评估期、交易成本或风险调整后表现，因此难以判断结果能否复现以及是否适用于实盘交易。

核心观点

  • 研究报告称，较强的大语言模型在加密货币交易中的表现可能不如较弱模型。
  • 文中将这一现象与较强模型偏好事实信息而非主观解读联系起来。
  • FS-ReasoningAgent在多智能体方法中区分事实推理与主观推理。
  • 报告的结果显示，BTC、ETH和SOL均有收益，但此处未提供实验细节。
  • 据报告，主观新闻在牛市中效果更好，而事实输入在熊市中效果更好。

标签

加密资产机器学习市场情绪回测
全文
# Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoning


# Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoning









While many studies show that more advanced LLMs excel in tasks such as mathematics and coding, we observe that in cryptocurrency trading, stronger LLMs sometimes underperform compared to weaker ones. To investigate this counterintuitive phenomenon, we examine how LLMs reason when making trading decisions. Our findings reveal that (1) stronger LLMs show a preference for factual information over subjectivity; (2) separating the reasoning process into factual and subjective components leads to higher profits. Building on these insights, we propose a multi-agent framework, FS-ReasoningAgent, which enables LLMs to recognize and learn from both factual and subjective reasoning. Extensive experiments demonstrate that this fine-grained reasoning approach enhances LLM trading performance in cryptocurrency markets, yielding profit improvements of 7\% in BTC, 2\% in ETH, and 10\% in SOL. Additionally, an ablation study reveals that relying on subjective news generates higher returns in bull markets, while focusing on factual information yields better results in bear markets. Code is available at https://github.com/Persdre/FS-ReasoningAgent.

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。