{"paper_id":"2408.06361","title":"Large Language Model Agent in Financial Trading: A Survey","authors":["Han Ding","Yinheng Li","Junhao Wang","Hang Chen","Doudou Guo","Yunbai Zhang"],"paper_date":"2024-07-26","paper_type":"survey-review","paper_url":"https://arxiv.org/pdf/2408.06361v1","page_url":"https://thequant.space/flowcharts/large-language-model-agent-in-financial-trading-a-survey/","scores":{"empirical_rigor":5.5,"math_complexity":3,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"We provide a comprehensive review of current research on using large language models as agents in financial trading.","quote":"In this survey, we provide a comprehensive review of the current research on using LLMs as agents in financial trading.","summary":"Trading is a highly competitive task that requires a combination of strategy, knowledge, and psychological fortitude. With the recent success of large language models(LLMs), it is appealing to apply the emerging intelligence of LLM agents in this competitive arena and understanding if they can…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Trading results are evaluated without accounting for transaction costs.","type":"execution","stated":"implied","quote":"One observation we had is that while both risk and profit metrics are commonly used, few studies consider trading costs in their evaluations. • Cumulative Return: Cumulative Return = \u0012𝑃𝑡−𝑃0 𝑃0 \u0013 × 100% where: – 𝑃𝑡is the ending price (or value) at time 𝑡 – 𝑃0 is the initial price (or value) at the beginning • Annualized Return Annualized Return = \u0012 𝑃𝑡 𝑃0 \u0013 1 𝑡 −1 where: – 𝑃𝑡is the ending price (or value) at time 𝑡 –","support":"full"}]},"datasets":{"status":"none_found","items":[],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"none"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"n/a","evidence_card":"no","evidence_card_quoted":true},"conflict_kind":"applicability","card_detail":null,"card_quote":"One observation we had is that while both risk and profit metrics are commonly used, few studies consider trading costs in their evaluations. • Cumulative Return: Cumulative Return = \u0012𝑃𝑡−𝑃0 𝑃0 \u0013 × 100% where: – 𝑃𝑡is the ending price (or value) at time 𝑡 – 𝑃0 is the initial price (or value) at the beginning • Annualized Return Annualized Return = \u0012 𝑃𝑡 𝑃0 \u0013 1 𝑡 −1 where: – 𝑃𝑡is the ending price (or value) at time 𝑡 –","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"LLM agents have achieved annualized returns ranging from 15% to 30% over the strongest baseline in backtesting with real market data.","kind":"performance","quote":"Our survey[8, 29, 53, 57] shows that LLM agents have achieved annualized return ranging from 15% to 30% over the strongest baseline during backtesting period with real market data, which demonstrates the great potential of using LLM in financial trading.","support":"full"},{"finding":"GPT‑3.5 is used more frequently than GPT‑4, indicating a preference for its cost‑effectiveness and lower latency.","kind":"other","quote":"Notably, GPT3.5 is even used more frequently than GPT4, indicating a preference on its cost-effectiveness and lower latency.","support":"full"},{"finding":"All surveyed LLM‑powered agents use textual financial data as input.","kind":"other","quote":"We found all LLM powered agents reviewed in this paper use textual financial data as input.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":0,"citations":{"cited_by_in_corpus":10,"by_independent_authors":10,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":7,"unclassified":2},"independent_papers":[{"paper":{"paper_id":"2505.07078","title":"Can LLM-based Financial Investing Strategies Outperform the Market in Long Run?","paper_date":"2025-05-11","authors":["Weixian Waylon Li","Hyeonjun Kim","Mihai Cucuringu","Tiejun Ma"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/can-llm-based-financial-investing-strategies-outperform-the/"},"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":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":2,"extracted_at":"2026-11-14T19:56:10Z"},"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/"}