LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management

2025-01-01

AI Summary

Cryptocurrency investment faces challenges including limited historical data, heterogeneous data sources, and opaque decision-making processes. Existing large language models (LLMs) lack domain-specific knowledge due to insufficient training on cryptocurrency-related data, hindering their ability to support professional investment decisions. To address this, we propose the first explainable multimodal multi-agent system tailored for crypto investment. It orchestrates a team of specialized agents that collaboratively perform time-series analysis, integration of research literature, and dynamic portfolio management. We introduce a novel confidence-based intra-group self-calibration mechanism and inter-group knowledge sharing, while fine-tuning agents jointly on multimodal time-series signals and domain-specific financial literature. Empirical evaluation from November 2023 to September 2024 demonstrates state-of-the-art performance across four metrics: classification accuracy, asset pricing error, Sharpe ratio, and decision interpretability—significantly outperforming both single-agent baselines and market benchmarks.

Technology Category

• Multiagent Systems: Mechanism Design
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Security and Privacy: Cryptocurrency and smart contracts

Abstract

Cryptocurrency investment is inherently difficult due to its shorter history compared to traditional assets, the need to integrate vast amounts of data from various modalities, and the requirement for complex reasoning. While deep learning approaches have been applied to address these challenges, their black-box nature raises concerns about trust and explainability. Recently, large language models (LLMs) have shown promise in financial applications due to their ability to understand multi-modal data and generate 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 have less domain-specific knowledge in 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. The expert training module fine-tunes agents using multi-modal historical data and professional investment literature, while the multi-agent investment module employs real-time data to make informed cryptocurrency investment decisions. Unique intrateam and interteam collaboration mechanisms enhance prediction accuracy 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 classification, asset pricing, portfolio, and explainability performance.

Problem

• Cryptocurrency Investment
• Large Language Models
• Data Heterogeneity

Innovation

• Cryptocurrency Investment
• Multi-agent Expert Systems
• Collaborative Decision-making