一种自适应多智能体比特币交易系统
An Adaptive Multi Agent Bitcoin Trading System
AI总结：
针对加密货币极端波动、难用静态模型建模的问题，本文提出一种基于大型语言模型（LLMs）的多智能体比特币交易系统，通过专业智能体分工及语言反馈机制优化决策，回测显示其在不同市场状态下表现优异，验证了语言反馈调优LLMs的有效性。
摘要：
本文提出了一种多智能体比特币交易系统，该系统利用大型语言模型（LLMs）在加密货币市场中生成alpha信号并进行投资组合管理。与股票不同，加密货币具有极端波动性，且受快速变化的市场情绪和监管公告的严重影响，这使得使用静态回归模型或仅基于历史数据训练的神经网络难以对其建模。所提出的框架通过将LLMs构建为专业智能体（负责技术分析、情绪评估、决策制定和性能反思）来克服这一挑战。智能体通过一种新颖的语言反馈机制随时间改进：Reflect智能体对交易决策提供每日和每周的自然语言批评，这些文本评估随后被注入智能体未来的提示中，使其无需权重更新或微调即可调整配置逻辑。对2024年7月至2025年4月比特币价格数据的回测显示，该系统在不同市场状态下持续表现优异：量化智能体在牛市阶段的回报率比买入持有策略高30%以上，整体收益达15%；情绪驱动智能体将横盘市场的小幅亏损转化为超过100%的收益。添加每周反馈进一步将总性能提升31%，并将熊市亏损减少10%。结果表明，语言反馈为针对金融目标调整LLMs提供了一种新的、可扩展且低成本的方法。
英文摘要：
This paper presents a Multi Agent Bitcoin Trading system that utilizes Large Language Models (LLMs) for alpha generation and portfolio management in the cryptocurrencies market. Unlike equities, cryptocurrencies exhibit extreme volatility and are heavily influenced by rapidly shifting market sentiments and regulatory announcements, making them difficult to model using static regression models or neural networks trained solely on historical data. The proposed framework overcomes this by structuring LLMs into specialised agents for technical analysis, sentiment evaluation, decision-making, and performance reflection. The agents improve over time via a novel verbal feedback mechanism where a Reflect agent provides daily and weekly natural-language critiques of trading decisions. These textual evaluations are then injected into future prompts of the agents, allowing them to adjust allocation logic without weight updates or finetuning. Back-testing on Bitcoin price data from July 2024 to April 2025 shows consistent outperformance across market regimes: the Quantitative agent delivered over 30\% higher returns in bullish phases and 15\% overall gains versus buy-and-hold, while the sentiment-driven agent turned sideways markets from a small loss into a gain of over 100\%. Adding weekly feedback further improved total performance by 31\% and reduced bearish losses by 10\%. The results demonstrate that verbal feedback represents a new, scalable, and low-cost approach of tuning LLMs for financial goals.
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。
