{"paper_id":"2502.13165","title":"HedgeAgents: A Balanced-aware Multi-agent Financial Trading System","authors":["Xiangyu Li","Yawen Zeng","Xiaofen Xing","Jin Xu","Xiangmin Xu"],"paper_date":"2025-02-17","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2502.13165v1","page_url":"https://thequant.space/flowcharts/hedgeagents-a-balanced-aware-multi-agent-financial-trading/","scores":{"empirical_rigor":6,"math_complexity":2,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes HedgeAgents, an innovative multi‑agent system that uses hedging strategies to improve robustness of financial trading.","quote":"This paper introduces an innovative multi-agent system, HedgeAgents, aimed at bolstering system robustness via ``hedging'' strategies.","summary":"As automated trading gains traction in the financial market, algorithmic investment strategies are increasingly prominent. While Large Language Models (LLMs) and Agent-based models exhibit promising potential in real-time market analysis and trading decisions, they still experience a significant…","strategy":"HedgeAgents multi-agent hedging system"},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"Bitcoin, foreign exchange, and Dow Jones component stocks","provider":"Yahoo Finance and the Alpaca News API","kind":"market-prices","access":"public","period":null,"universe":"Bitcoin, FX, DJIA constituents","quote":"These data were sourced from reputable financial databases, namely Yahoo Finance and the Alpaca News API.","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"These data were sourced from reputable financial databases, namely Yahoo Finance and the Alpaca News API.","mentions":1,"used_in":1}],"sample":{"start":"2021-01","end":"2023-12","market":"multiple asset classes (crypto, stocks, FX)","asset_class":"multi-asset","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":false,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"no","evidence_card":"yes","evidence_card_quoted":true},"conflict_kind":"polarity","card_detail":"Total cost of $15 over three years, averaging about 2 cents per day.","card_quote":"Notably, our system has accumulated a total cost of $15 over the three years, averaging only 2 cents per day!","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"HedgeAgents achieved a 70% annualized return and a 400% total return over a three‑year period.","kind":"performance","quote":"our HedgeAgents attained a 70% annualized return and a 400% total return over a period of 3 years."},{"finding":"Removing the ESC module reduces the ENT metric by 16.63% to 2.61, the largest drop among modules.","kind":"performance","quote":"When this module is removed, the ENT metric decreases by 16.63% to 2.61, showing the largest drop"},{"finding":"Removing the BAC module lowers annualized return by 37.75% to 44.57%; retaining only BAC yields the highest single‑module return of 45.58%.","kind":"performance","quote":"After removing this module, the annualized return drops by 37.75% to 44.57%, the lowest among the three single-module experiments; however, when only this module is retained, the annualized return reaches the highest value of 45.58% for a single module."},{"finding":"Removing the EMC module raises maximum drawdown by 71.93% to 24.44% and cuts Sharpe ratio by 19.86% to 1.93; keeping only EMC gives the best drawdown and Sharpe among single modules.","kind":"performance","quote":"After removing this module, the maximum drawdown rate increases by 71.93% to 24.44%, and the Sharpe ratio decreases by 19.86% to 1.93; however, when only this module is retained, both the maximum drawdown rate and Sharpe ratio achieve the best levels among single modules."},{"finding":"In a Bitcoin‑only setting, HedgeAgents achieved a cumulative return of about 210%, far exceeding all baselines.","kind":"performance","quote":"The Bitcoin-only setting showcased HedgeAgents’ exceptional management of high‑volatility assets, achieving a cumulative return of about 210%, far exceeding all baseline models."}],"reported_performance":{"strategy":"HedgeAgents multi-agent hedging system","sharpe":2.41,"sharpe_benchmark":null,"annual_return_pct":70,"total_return_pct":400,"max_drawdown_pct":11.02},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":40,"citations":{"cited_by_in_corpus":10,"by_independent_authors":9,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":7,"unclassified":3},"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":"2026-11-14T17:45:06Z"},"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/"}