{"paper_id":"2510.08068","title":"An Adaptive Multi Agent Bitcoin Trading System","authors":["Aadi Singhi"],"paper_date":"2025-10-09","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.08068v2","page_url":"https://thequant.space/flowcharts/an-adaptive-multi-agent-bitcoin-trading-system/","scores":{"empirical_rigor":6,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a multi‑agent Bitcoin trading system that uses large language models with a dual verbal feedback mechanism for alpha generation and portfolio management.","quote":"This paper presents a Multi Agent Bitcoin Trading system that utilizes Large Language Models (LLMs) for alpha generation and portfolio management in the cryptocurrencies market.","summary":"This paper presents a Multi Agent Bitcoin Trading system that utilizes Large Language Models (LLMs) for alpha generation and portfolio management in the cryptocurrencies market. Unlike equities, cryptocurrencies exhibit extreme volatility and are heavily influenced by rapidly shifting market…","strategy":"Adaptive Multi Agent Bitcoin Trading System"},"assumptions":{"status":"available","items":[{"assumption":"Bitcoin price movements are driven primarily by non‑fundamental forces such as regulatory announcements, influencer statements, and speculation.","type":"market","stated":"explicit","quote":"Bitcoin’s price is largely driven by non-fundamental forces such as regulatory announcements, influencer statements, and speculative"},{"assumption":"The system trades once per day using daily closing prices, ignoring intraday dynamics.","type":"execution","stated":"implied","quote":"The system was evaluated on daily Bitcoin data from July 2024 to April 2025."},{"assumption":"LLMs can effectively process real‑time textual signals without parameter updates.","type":"model","stated":"explicit","quote":"LLMs offer a potential solution to this unpredictability, as they are particularly suited for large-scale textual analysis and pattern recognition."},{"assumption":"Transaction costs, slippage and market impact are not incorporated into the reported headline results.","type":"execution","stated":"implied","quote":"even highly accurate models may fail if execution costs, slippage, or regime shifts negate expected returns."}]},"datasets":{"status":"available","items":[{"name":"daily Bitcoin price data","provider":null,"kind":"market-prices","access":"unknown","period":"July 2024 to April 2025","universe":"Bitcoin","quote":"The system was evaluated on daily Bitcoin data from July 2024 to April 2025."},{"name":"news data via GNews API","provider":"GNews","kind":"text-news","access":"public","period":null,"universe":null,"quote":"First, news data from trusted financial outlets (e.g., CNBC, Yahoo Finance, Forbes, Business Insider, Seeking Alpha, and Fortune) is aggregated via the GNews API"},{"name":"Fear and Greed Index","provider":"Alternative.me","kind":"alternative","access":"public","period":null,"universe":null,"quote":"Second, the Fear and Greed Index, obtained from Alternative.me, provides a composite daily score ranging from extreme fear to extreme greed"},{"name":"Senticrypt social media sentiment scores","provider":"Senticrypt","kind":"alternative","access":"public","period":null,"universe":null,"quote":"Finally, social media sentiment scores are collected through the Senticrypt API, which processes Twitter discussions to quantify retail investor mood in real time"}],"known":[{"id":"twitter","name":"Twitter / X","provider":"X Corp.","kind":"text-news","access":"public","quote":"Finally, social media sen-timent scores are collected through the Senticrypt API, which processes Twitter discussions to quantify retail in-vestor mood in real time [2].Together, these inputs al-low the agent to evaluate both structured and unstructured sentiment signals, ensuring that its predictions incorpo-rate news-driven shocks, aggregated market psychology, and the daily pulse of social platforms.","mentions":1,"used_in":1},{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"First, news data from trusted finan-cial outlets (e.g., CNBC, Yahoo Finance, Forbes, Business Insider, Seeking Alpha, and Fortune) is aggregated via the GNews API [3], ensuring coverage of regulatory an-nouncements, macroeconomic shifts, and key narratives shaping sentiment.","mentions":1,"used_in":1}],"sample":{"start":"2024-07","end":"2025-04","market":"Bitcoin","asset_class":"crypto","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":"even highly accurate models may fail if execution costs, slippage, or regime shifts negate expected returns.","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"even highly accurate models may fail if execution costs, slippage, or regime shifts negate expected returns.","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The Quantitative agent delivered over 30% higher returns in bullish phases and 15% overall gains versus a buy‑and‑hold benchmark.","kind":"performance","quote":"the Quantitative agent delivered over 30% higher returns in bullish phases and 15% overall gains versus buy-and-hold"},{"finding":"The sentiment‑driven agent turned sideways markets from a small loss into a gain of over 100%.","kind":"performance","quote":"the sentiment-driven agent turned sideways markets from a small loss into a gain of over 100%"},{"finding":"Adding weekly verbal feedback improved total performance by 31% and reduced bearish losses by 10%.","kind":"performance","quote":"Adding weekly feedback further improved total performance by 31% and reduced bearish losses by 10%"}],"reported_performance":{"strategy":"Adaptive Multi Agent Bitcoin Trading System","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"none","headline_out_of_sample":false}},"independent_evidence":{"status":"available","supports":[],"contradicts":[{"paper":{"paper_id":"2510.15949","title":"ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination","paper_date":"2025-10-10","authors":["Charidimos Papadakis","Angeliki Dimitriou","Giorgos Filandrianos","Maria Lymperaiou","Konstantinos Thomas","Giorgos Stamou"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/atlas-adaptive-trading-with-llm-agents-through-dynamic-prom/"},"question":"Does providing feedback to adaptive multi‑agent trading systems improve performance?","this_paper_finding":"Adding weekly verbal feedback improved total performance by 31% and reduced bearish losses by 10%.","other_paper_finding":"Reflection‑based feedback fails to provide systematic gains and can be inconsistent across models.","other_paper_quote":"while standard reflection proves inconsistent","note":"A shows +31% total performance and -10% bearish losses with weekly verbal feedback; B finds reflection‑based feedback gives no systematic gains and is inconsistent across models.","confidence":0.628}],"qualifies":[],"compared_with":14,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"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":"2026-11-14T17:25:12Z"},"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/"}