{"paper_id":"2501.00826","title":"LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management","authors":["Yichen Luo","Yebo Feng","Jiahua Xu","Paolo Tasca","Yang Liu"],"paper_date":"2025-01-01","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2501.00826v2","page_url":"https://thequant.space/flowcharts/llm-powered-multi-agent-system-for-automated-crypto-portfoli/","scores":{"empirical_rigor":6,"math_complexity":3,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes an explainable, multi‑modal, multi‑agent framework for cryptocurrency investment, comprising expert training and multi‑agent investment modules.","quote":"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 capitaliz","summary":"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…","strategy":"Multi-agent cryptocurrency investment framework"},"assumptions":{"status":"available","items":[{"assumption":"Only the top 30 high‑capitalization cryptocurrencies are considered, excluding low‑liquidity assets.","type":"market","stated":"explicit","quote":"The rationale for including only high‑capitalization cryptocurrencies is that those with low market capitalization often exhibit pricing dynamics that differ significantly from high‑liquidity cryptocurrencies, partly due to risks such as pump-and-dump schemes."},{"assumption":"Data from November 2023 to September 2024 is used as a test set to avoid information leakage from ChatGPT‑4o’s training data.","type":"data","stated":"explicit","quote":"to September 2024 as the test set, given that ChatGPT‑4o’s training data extends only up to October 2023."},{"assumption":"Portfolios are equal‑weighted when evaluating performance.","type":"execution","stated":"explicit","quote":"All portfolios are equal‑weighted."},{"assumption":"Risk‑factor quintiles are determined using cross‑sectional data and the initial two years of market‑related factors.","type":"statistical","stated":"explicit","quote":"Risk factors are categorized into five quintiles: “Very Low”, “Low”, “Medium”, “High”, and “Very High”. The quintile cutoffs are determined using cross‑sectional data for crypto‑related factors and the initial two years of data for market‑related factors."},{"assumption":"Real‑time data from Coingecko, Blockchain.info, Coin Metrics, and news from Cointelegraph are sufficient for investment decisions.","type":"data","stated":"implied","quote":"are computed using OHLC price data, trading volume, and market capitalization from Coingecko, along with on‑chain data sourced from Blockchain.info and Coin Metrics."}]},"datasets":{"status":"available","items":[{"name":"Cryptocurrency price, volume and market‑cap data","provider":"Coingecko","kind":"market-prices","access":"public","period":"June 2023 to September 2024","universe":"Top 30 cryptocurrencies by market capitalization","quote":"The 30‑day candlestick charts (Fig. 1a) and binary price trends (Fig. 1b) are derived from open high low and close (OHLC) price data and trading volume provided by Coingecko.","known_id":"coingecko"},{"name":"On‑chain data","provider":"Blockchain.info and Coin Metrics","kind":"crypto-onchain","access":"public","period":"June 2023 to September 2024","universe":"Top 30 cryptocurrencies by market capitalization","quote":"are computed using OHLC price data, trading volume, and market capitalization from Coingecko, along with on‑chain data sourced from Blockchain.info and Coin Metrics."},{"name":"Cryptocurrency news headlines","provider":"Cointelegraph","kind":"text-news","access":"public","period":"June 2023 to September 2024","universe":"Top 30 cryptocurrencies by market capitalization","quote":"news headline data (Fig. 1d) is obtained through web crawling from Cointelegraph."}],"known":[{"id":"coingecko","name":"CoinGecko","provider":"CoinGecko","kind":"market-prices","access":"public","quote":"This agent utilizes tools to gather data from leading cryptocurrency providers, includ-ing Coingecko, Blockchain.info, Coin Metrics, and Cointelegraph.","mentions":4,"used_in":2}],"sample":{"start":"2023-11","end":"2024-08","market":"Top 30 cryptocurrencies by market cap","asset_class":"crypto","frequency":"weekly"},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The multi‑agent framework achieves the highest classification accuracy for cryptocurrency price‑trend prediction, outperforming a single fine‑tuned GPT‑4o model.","kind":"predictive-accuracy","quote":"The multi‑agent framework outperforms a single GPT‑4o model with fine‑tuning, demonstrating that multiple expert agents, each trained with domain‑specific knowledge, perform better than a single agent trained with a comprehensive dataset for cryptocurrency price trend prediction."},{"finding":"Overall, the proposed framework outperforms single‑agent models and market benchmarks in both classification accuracy and asset‑pricing performance.","kind":"performance","quote":"Our experimental results demonstrate that our model outperforms single‑agent models, both with and without fine‑tuning, in terms of classification accuracy and asset pricing performance. Furthermore, we show that our framework surpasses market benchmarks in portfolio performance."}],"reported_performance":{"strategy":"Multi-agent cryptocurrency investment framework","sharpe":1.5425,"sharpe_benchmark":1.3781,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":20,"citations":{"cited_by_in_corpus":3,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":2},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:48:21Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}