{"paper_id":"2407.18957","title":"When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments","authors":["Chong Zhang","Xinyi Liu","Zhongmou Zhang","Mingyu Jin","Lingyao Li","Zhenting Wang","Wenyue Hua","Dong Shu","Suiyuan Zhu","Xiaobo Jin","Sujian Li","Mengnan Du","Yongfeng Zhang"],"paper_date":"2024-07-15","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2407.18957v4","page_url":"https://thequant.space/flowcharts/when-ai-meets-finance-stockagent-large-language-model-bas/","scores":{"empirical_rigor":8,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes StockAgent, a multi‑agent AI framework driven by large language models to simulate investor trading behavior in realistic market conditions.","quote":"We have developed a multi-agent AI system called StockAgent, driven by LLMs, designed to simulate investors' trading behaviors in response to the real stock market.","summary":"Can AI Agents simulate real-world trading environments to investigate the impact of external factors on stock trading activities (e.g., macroeconomics, policy changes, company fundamentals, and global events)? These factors, which frequently influence trading behaviors, are critical elements in the…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"StockAgent assumes basic common sense of stock market trading and can make profitable trades to maximize profits.","type":"model","stated":"explicit","quote":"StockAgent Setup Assuming basic common sense of stock market trading, our StockAgent can make profitable trades to maximize profits."},{"assumption":"StockAgent actions are limited to buy, sell, hold, long and short.","type":"execution","stated":"explicit","quote":"We restrict the StockAgent actions to buy, sell, hold, long and short."},{"assumption":"Agents may incur debt, but the amount cannot exceed the value of their capital.","type":"market","stated":"explicit","quote":"Agents may incur debt, with the amount not exceeding the value of their capital."},{"assumption":"Transaction stamp tax follows American market rules with a fee of 0.005 per share, minimum 1, maximum 5.95 currency units.","type":"execution","stated":"explicit","quote":"We set the transaction stamp tax according to the rules of the American stock market. We put the transaction fee of each Agent in purchasing shares to 0.005 currency units per share, the minimum transaction fee of each transaction is 1 currency unit, and the maximum transaction fee is 5.95 currency units."},{"assumption":"The simulation covers one year of 264 trading days, split into four quarters of 66 days each.","type":"market","stated":"explicit","quote":"Trading Year: The simulation covers one year comprising 264 trading days, divided into four quarters of 66 trading days each."},{"assumption":"Deposit rate for companies and individuals is set to 0% reflecting low‑interest environments.","type":"market","stated":"explicit","quote":"Interest Rates and Deposits: For companies and individuals, the deposit rate is 0%, reflecting contemporary low-interest-rate environments."}]},"datasets":{"status":"available","items":[{"name":"Stock A and Stock B financial reports","provider":null,"kind":"fundamentals","access":"unknown","period":null,"universe":"two anonymized US stocks","quote":"We use their financial reports—specifically, the balance sheet, income statement, and cash flow statement—as the basis for calculating the initial settings of our simulation."},{"name":"External economic and financial events","provider":null,"kind":"macro","access":"unknown","period":"2014-2019","universe":null,"quote":"We use external economic and financial events from 2014 to 2019 to align our valuation and volume energy calculations with reality."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Transaction fee of 0.005 currency units per share, with a minimum of 1 and a maximum of 5.95 currency units per transaction.","quote":"We set the transaction stamp tax according to the rules of the American stock market. We put the transaction fee of each Agent in purchasing shares to 0.005 currency units per share, the minimum transaction fee of each transaction is 1 currency unit, and the maximum transaction fee is 5.95 currency units.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Transaction fee of 0.005 currency units per share, with a minimum of 1 and a maximum of 5.95 currency units per transaction.","card_quote":"We set the transaction stamp tax according to the rules of the American stock market. We put the transaction fee of each Agent in purchasing shares to 0.005 currency units per share, the minimum transaction fee of each transaction is 1 currency unit, and the maximum transaction fee is 5.95 currency units.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"GPT‑driven agents trade less frequently but with significantly higher volume than Gemini‑driven agents.","kind":"performance","quote":"Although the GPT-driven AI Agents trades less frequently, the volume is significantly higher than that driven by Gemini."},{"finding":"Gemini‑based agents show more consistent group behavior, while GPT‑based agents display greater individual differences.","kind":"statistical","quote":"Gemini-based agents exhibit similar characteristics and more consistent group behavior. In contrast, GPT-driven agents display greater individual differences and subjective decision-making abilities."},{"finding":"Removing earnings reports and interest‑rate changes caused many agents to shift from losses to profits, increasing overall profitability.","kind":"performance","quote":"Interestingly, the elimination of earnings reports and interest rate changes caused many agents to shift from losses to profits, increasing the overall profitability of the group."},{"finding":"Without the BBS sharing feature, agents act more cautiously and avoid large transactions.","kind":"other","quote":"Without the BBS sharing feature, agents tend to act more cautiously and avoid large transactions."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":33,"citations":{"cited_by_in_corpus":17,"by_independent_authors":15,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":15,"unclassified":2},"independent_papers":[],"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/MingyuJ666/Stockagent","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":"2026-11-14T16:36:17Z"},"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/"}