{"paper_id":"2412.20138","title":"TradingAgents: Multi-Agents LLM Financial Trading Framework","authors":["Yijia Xiao","Edward Sun","Di Luo","Wei Wang"],"paper_date":"2024-12-28","paper_type":"perspective-policy","paper_url":"https://arxiv.org/pdf/2412.20138v7","page_url":"https://thequant.space/flowcharts/tradingagents-multi-agents-llm-financial-trading-framework/","scores":{"empirical_rigor":6,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes TradingAgents, a novel multi-agent LLM-powered stock trading framework with specialized analyst and trader roles.","quote":"TradingAgents proposes a novel stock trading framework inspired by trading firms, featuring LLM-powered agents in specialized roles such as fundamental analysts, sentiment analysts, technical analysts, and traders with varied risk profiles.","summary":"Significant progress has been made in automated problem-solving using societies of agents powered by large language models (LLMs). In finance, efforts have largely focused on single-agent systems handling specific tasks or multi-agent frameworks independently gathering data. However, the…","strategy":"TradingAgents"},"assumptions":{"status":"available","items":[{"assumption":"The framework assumes the existence of defined teams of specialized agents (analyst team, researcher team, trader team, risk manager).","type":"model","stated":"explicit","quote":"More specifically, TradingAgents assumes the following teams."}]},"datasets":{"status":"available","items":[{"name":"Multi-asset multi-modal financial dataset","provider":null,"kind":"other","access":"unknown","period":"January 1st, 2024 to March 29th, 2024","universe":"Apple, Nvidia, Microsoft, Meta, Google, and more","quote":"Our multi-modal dataset integrates historical stock prices, news articles, social media sentiment, insider transactions, financial statements, and 60 technical indicators per asset."}],"known":[],"sample":{"start":"2024-01","end":"2024-03","market":"US equities","asset_class":"multi-asset","frequency":"daily"},"data_resolution":"daily"},"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":"TradingAgents outperforms baseline strategies in cumulative return, Sharpe ratio, and maximum drawdown.","kind":"performance","quote":"Experiments demonstrate that TradingAgents outperforms traditional trading strategies and baselines in cumulative return, Sharpe ratio, and other critical financial metrics."},{"finding":"The framework shows superiority over baseline models with notable improvements in cumulative returns, Sharpe ratio, and maximum drawdown.","kind":"performance","quote":"Detailed architecture and extensive experiments reveal its superiority over baseline models, with notable improvements in cumulative returns, Sharpe ratio, and maximum drawdown"}],"reported_performance":{"strategy":"TradingAgents","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":24.9,"total_return_pct":23.21,"max_drawdown_pct":2.11},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":30,"citations":{"cited_by_in_corpus":38,"by_independent_authors":36,"how_cited":{"used_as_baseline":0,"uses_method_or_data":2,"extends":0,"discusses_findings":0,"mentions":31,"unclassified":5},"independent_papers":[{"paper":{"paper_id":"2610.04040","title":"Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents","paper_date":"2026-10-02","authors":["Mingyang","Chen","Yida","Xu","Huiwen","Chen"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/agent-policy-value-audit-separating-transition-composition-from-event-selection/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2603.21330","title":"FinRL-X: An AI-Native Modular Infrastructure for Quantitative Trading","paper_date":"2026-03-22","authors":["Hongyang Yang","Boyu Zhang","Yang She","Xinyu Liao","Xiaoli Zhang"],"empirical_rigor":6.5,"page_url":"https://thequant.space/flowcharts/finrl-x-an-ai-native-modular-infrastructure-for-quantitative-trading/"},"how":"uses_method_or_data","quote":null}],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/TauricResearch/TradingAgents","note":null},"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":"2026-11-14T16:28:08Z"},"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/"}