Go to ACL ARR 2026 January homepageLLM-Powered Multi-Agent System for Automated Crypto Portfolio Management
Keywords: Multi-agent System, Cryptocurrency, Portfolio Management
Abstract: Cryptocurrency investment is non-trivial due to its short history, the involvement of multi-modal data, and the need for complex reasoning. While deep learning has addressed some of these challenges, its ``black-box" nature limits trust and explainability. Recently, large language models (LLMs) have shown promise in financial applications by effectively understanding multi-modal data and generating explainable decisions. However, single LLM faces limitations in complex, comprehensive tasks such as asset investment. These limitations are even more pronounced in cryptocurrency investment, where LLMs often lack sufficient domain-specific knowledge within their training corpora.
To overcome these challenges, we propose an explainable, multi-modal, multi-agent framework for cryptocurrency investment. Our framework uses specialized agents that collaborate within and across teams to handle subtasks such as data analysis, literature integration, and investment decision-making for the top 30 cryptocurrencies by market capitalization using multi-modal data. Unique intrateam and interteam collaboration mechanisms enhance predictability by adjusting final predictions based on confidence levels within agent teams and facilitating information sharing between teams. Empirical evaluation using data from November 2023 to September 2024 demonstrates that our framework outperforms single-agent models and market benchmarks in multiple metrics. Our framework delivers an annualized cumulative return of 108.32% and an annualized Sharpe ratio of 1.5425 in portfolio performance and generates statistically significant long-short portfolio returns in asset pricing.
Paper Type: Long
Research Area: AI/LLM Agents
Research Area Keywords: NLP Applications, Language Modeling
Contribution Types: Model analysis & interpretability, Data analysis
Languages Studied: English
Submission Number: 2713
Loading