{"paper_id":"2511.03628","title":"LiveTradeBench: Seeking Real-World Alpha with Large Language Models","authors":["Haofei Yu","Fenghai Li","Jiaxuan You"],"paper_date":"2025-11-05","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2511.03628v1","page_url":"https://thequant.space/flowcharts/livetradebench-seeking-real-world-alpha-with-large-language/","scores":{"empirical_rigor":6,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes LiveTradeBench, a live multi‑market trading environment for evaluating LLM‑based agents in realistic portfolio‑management tasks.","quote":"we introduce LiveTradeBench, a live trading environment for evaluating LLM agents in realistic and evolving markets.","summary":"Large language models (LLMs) achieve strong performance across benchmarks–from knowledge quizzes and math reasoning to web-agent tasks–but these tests occur in static settings, lacking real dynamics and uncertainty. Consequently, they evaluate isolated reasoning or problem-solving rather than…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Trades have negligible market impact because assets are highly liquid.","type":"market","stated":"explicit","quote":"Since we focus on highly liquid assets such as Nvidia (NVDA) stocks and trending Polymarket markets to make up the portfolio, the agent’s individual trades exert negligible influence on real‑world prices. This assumption justifies modeling the simulated transition function T as closely aligned with the real world."},{"assumption":"Default action space is long‑only (no short positions).","type":"model","stated":"explicit","quote":"By default, we assume a long‑only setting where a(i)_t ≥0 for all i."},{"assumption":"Observation and action spaces are limited by LLM context length.","type":"data","stated":"explicit","quote":"The current framework constrains both the observation and action spaces due to the limited context length of existing LLMs."},{"assumption":"Transaction fees, bid‑ask spreads, and liquidity constraints are ignored.","type":"execution","stated":"explicit","quote":"Our current environment and evaluation do not account for transaction fees, bid–ask spreads, liquidity constraints, or other real‑world trading frictions."}]},"datasets":{"status":"available","items":[{"name":"Live market data (U.S. stocks)","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":"highly liquid assets such as Nvidia (NVDA) stocks","quote":"LiveTradeBench streams live market data, financial news, and social signals, eliminating the dependence on offline backtesting and thereby avoiding information leakage from the root while capturing real‑world uncertainty and feedback."},{"name":"Polymarket prediction markets","provider":null,"kind":"text-news","access":"unknown","period":null,"universe":"trending Polymarket markets","quote":"LiveTradeBench streams live market data, financial news, and social signals, eliminating the dependence on offline backtesting and thereby avoiding information leakage from the root while capturing real‑world uncertainty and feedback."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":"Our current environment and evaluation do not account for transaction fees, bid–ask spreads, liquidity constraints, or other real‑world trading frictions.","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"Our current environment and evaluation do not account for transaction fees, bid–ask spreads, liquidity constraints, or other real‑world trading frictions.","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"LMArena benchmark scores have virtually no correlation with trading returns (Spearman 0.054 for stocks, –0.38 for Polymarket).","kind":"performance","quote":"In the stock market, the Spearman correlation between LMArena scores and cumulative returns is only 0.054—virtually no relationship. In Polymarket, the correlation drops to –0.38, meaning models with higher general language ability often perform worse in the dynamic market."},{"finding":"Models exhibit distinct portfolio‑management styles, e.g., GPT‑5 diversifies across many stocks while Llama4‑Scout keeps a high cash ratio.","kind":"performance","quote":"Llama4‑Scout maintains a persistently high cash ratio (above 20%), reflecting a more cautious liquidity stance."},{"finding":"Reasoning‑focused LLMs do not outperform others and show higher volatility, indicating over‑adjustment.","kind":"negative","quote":"do not outperform others in trading performance. Instead, they exhibit substantially higher volatility (>140 in Polymarket), implying over‑adjustment during the decision process."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":24,"citations":{"cited_by_in_corpus":4,"by_independent_authors":3,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":1,"mentions":2,"unclassified":1},"independent_papers":[{"paper":{"paper_id":"2603.17692","title":"Can Blindfolded LLMs Still Trade? An Anonymization-First Framework for Portfolio Optimization","paper_date":"2026-03-18","authors":["Joohyoung Jeon","Hongchul Lee"],"empirical_rigor":7.5,"page_url":"https://thequant.space/flowcharts/can-blindfolded-llms-still-trade-an-anonymization-first-framework-for-portfolio/"},"how":"discusses_findings","quote":"LiveTradeBench [CITED] evaluated LLM agents in real-time environments, and models that"}],"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/ulab-uiuc/live-trade-bench","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":"2026-11-14T17:22:50Z"},"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/"}