arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.12464cs.MA
收藏

通过事实-主观性感知推理探索大语言模型加密货币交易

Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoning

Qian Wang, Yuchen Gao, Zhenheng Tang, Bingqiao Luo, Nuo Chen, Bingsheng He

AI总结:

本文针对更强LLM在加密货币交易中反而不如弱模型的现象,提出事实-主观性感知的多智能体框架FS-ReasoningAgent,将推理分解为事实性与主观性成分,在BTC、ETH、SOL上分别提升7%、2%、10%的利润。

摘要:

尽管许多研究表明,更先进的大语言模型(LLM)在数学和编程等任务中表现更出色,但我们观察到,在加密货币交易中,更强的LLM有时反而比更弱的LLM表现更差。为探究这一反直觉现象,我们考察了LLM在做出交易决策时的推理方式。我们的研究发现:(1)更强的LLM表现出对事实信息而非主观信息的偏好;(2)将推理过程分解为事实性成分和主观性成分能够带来更高的利润。基于这些见解,我们提出了一个多智能体框架FS-ReasoningAgent,使LLM能够识别并学习事实性推理和主观性推理。大量实验表明,这种细粒度推理方法提升了LLM在加密货币市场中的交易表现,在BTC上实现了7%的利润提升,在ETH上实现了2%的利润提升,在SOL上实现了10%的利润提升。此外,消融研究揭示,在牛市中依赖主观新闻能产生更高收益,而在熊市中关注事实信息则能取得更好结果。代码可在https://github.com/Persdre/FS-ReasoningAgent获取。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑