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

arXiv: https://arxiv.org/abs/2501.00826 · HTML: https://mlsanity.com/paper/2501.00826/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 1 Jan 2025.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 22 of 22)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [Large Language Models in Finance: A Survey](https://mlsanity.com/paper/2311.10723/) (2023)
- [PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance](https://mlsanity.com/paper/2306.05443/) (2023)
- [FinGPT: Democratizing Internet-scale Data for Financial Large Language Models](https://mlsanity.com/paper/2307.10485/) (2023)
- [Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models](https://mlsanity.com/paper/2402.03659/) (2024)
- [AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration](https://mlsanity.com/paper/2404.11943/) (2024)
- [Automate Strategy Finding with LLM in Quant Investment](https://mlsanity.com/paper/2409.06289/) (2024)
- [TradExpert: Revolutionizing Trading with Mixture of Expert LLMs](https://mlsanity.com/paper/2411.00782/) (2024)
- [A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading](https://mlsanity.com/paper/2407.09546/) (2024)
- [Multimodal Gen-AI for Fundamental Investment Research](https://mlsanity.com/paper/2401.06164/) (2023)
- [FinVision: A Multi-Agent Framework for Stock Market Prediction](https://mlsanity.com/paper/2411.08899/) (2024)

## Built on by (most cited first, 20 of 20)

- [Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation](https://mlsanity.com/paper/2510.11620/) (2025)
- [Debt Collection Negotiations with Large Language Models: An Evaluation System and Optimizing Decision Making with Multi-Agent](https://mlsanity.com/paper/2502.18228/) (2025)
- [SoK: Security of Autonomous LLM Agents in Agentic Commerce](https://mlsanity.com/paper/2604.15367/) (2026)
- [Calibration-Aware Policy Optimization for Reasoning LLMs](https://mlsanity.com/paper/2604.12632/) (2026)
- [SoK: Security and Privacy of AI Agents for Blockchain](https://mlsanity.com/paper/2509.07131/) (2025)
- [Giving AI Agents Access to Cryptocurrency and Smart Contracts Creates New Vectors of AI Harm](https://mlsanity.com/paper/2507.08249/) (2025)
- [PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Management](https://mlsanity.com/paper/2605.27887/) (2026)
- [Can Large Language Models Develop Gambling Addiction?](https://mlsanity.com/paper/2509.22818/) (2025)
- [Synthesizing Behaviorally-Grounded Reasoning Chains: A Data-Generation Framework for Personal Finance LLMs](https://mlsanity.com/paper/2509.14180/) (2025)
- [An Adaptive Multi Agent Bitcoin Trading System](https://mlsanity.com/paper/2510.08068/) (2025)
- [Resisting Manipulative Bots in Meme Coin Copy Trading: A Multi-Agent Approach with Chain-of-Thought Reasoning](https://mlsanity.com/paper/2601.08641/) (2026)
- [Paper Agents, Paper Gains: An Empirical Analysis of DeFi Investment Agents](https://mlsanity.com/paper/2605.29174/) (2026)
- [PartnerMAS: An LLM Hierarchical Multi-Agent Framework for Business Partner Selection on High-Dimensional Features](https://mlsanity.com/paper/2509.24046/) (2025)
- [LATTICE: Evaluating Decision Support Utility of Crypto Agents](https://mlsanity.com/paper/2604.26235/) (2026)
- [Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems](https://mlsanity.com/paper/2605.24490/) (2026)
- [DeXposure-Claw: An Agentic System for DeFi Risk Supervision](https://mlsanity.com/paper/2606.19501/) (2026)
- [CSTrader: A Testbed for Language-Grounded Trading in a Community-Driven Virtual Asset Market](https://mlsanity.com/paper/2606.31461/) (2026)
- [Can Agentic Trading Systems Pay for Their Own Intelligence?](https://mlsanity.com/paper/2607.10286/) (2026)
- [Regime-Aware Portfolio Management via Retrieval-Augmented LLM-Guided Expert Switching](https://mlsanity.com/paper/2608.28252/) (2026)
- [FaVOR: LLM-Based Agentic Framework for Factor Mining via Empirical Validation](https://mlsanity.com/paper/2608.30192/) (2026)

## Abstract (arXiv)

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.