Cryptocurrency portfolio management requires the fusion of heterogeneous multi-modal signals, including structured price and on-chain time series, unstructured news text, and technical indicators, under high-volatility and real-time constraints. While deep learning approaches show predictive capability, their opacity limits practical adoption, and single large language model (LLM) agents struggle to process the breadth of modality-specific inputs needed for robust decision-making. We propose a multi-agent system (MAS) framework in which three modality-specialised agents, a Crypto Agent for market dynamics, a News Agent for weekly news sentiment, and a Trading Agent for signal fusion and portfolio execution, decompose the task across three communication architectures: hierarchical, collaborative, and debate. We evaluate four capability configurations: zero-shot, chain-of-thought (CoT), retrieval-augmented generation (RAG), and skill-augmented. In a 52-week backtest over calendar year 2025 across the top 15 L1 blockchain native cryptocurrencies by market capitalisation as of January 2025, the best configuration, Hierarchical (Skill), achieves a cumulative return of 133.52% and a Sharpe ratio of 1.502, outperforming single-agent variants, passive benchmarks, and deep learning baselines. An ablation study identifies the Crypto Agent as the most critical component, with its removal reducing cumulative return by 42.57 percentage points. A cross-model comparison further shows that MAS outperforms the single-agent baseline under GPT-4o, GPT-5, and Claude Sonnet 4.5, suggesting that the benefit of multi-agent coordination is model-agnostic. Unlike black-box deep learning models, every portfolio decision is traceable to explicit agent reasoning, offering an interpretable and effective approach to multi-modal cryptocurrency portfolio management.

翻译：加密货币投资组合管理需要在高度波动和实时约束下融合异构多模态信号，包括结构化的价格和链上时间序列、非结构化新闻文本以及技术指标。尽管深度学习方法展现出预测能力，但其不透明性限制了实际应用，而单一大型语言模型智能体难以处理稳健决策所需的多模态特定输入信息广度。我们提出一个多智能体系统框架，其中三个模态专业化智能体——负责市场动态的加密智能体、负责每周新闻情绪的新闻智能体、以及负责信号融合与投资组合执行交易智能体——通过三种通信架构分解任务：层级式、协作式和辩论式。我们评估了四种能力配置：零样本、思维链、检索增强生成和技能增强。在2025年1月市值排名前15的L1区块链原生加密货币的52周回测（覆盖2025日历年）中，性能最佳的配置——层级式（技能增强）实现了133.52%的累计收益率和1.502的夏普比率，优于单智能体变体、被动基准和深度学习基线。消融研究发现加密智能体是最关键组件，移除该组件会导致累计收益率下降42.57个百分点。跨模型比较进一步表明，在GPT-4o、GPT-5和Claude Sonnet 4.5下，多智能体系统均优于单智能体基线，表明多智能体协调的收益具有模型无关性。与黑箱深度学习模型不同，每项投资组合决策均可追溯到明确的智能体推理过程，为多模态加密货币投资组合管理提供了可解释且有效的方法。