{"paper_id":"2509.05080","title":"MM-DREX: Multimodal-Driven Dynamic Routing of LLM Experts for Financial Trading","authors":["Yang Chen","Yueheng Jiang","Zhaozhao Ma","Yuchen Cao","Jacky Keung","Kun Kuang","Leilei Gan","Yiquan Wu","Fei Wu"],"paper_date":"2025-09-05","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2509.05080v2","page_url":"https://thequant.space/flowcharts/mm-drex-multimodal-driven-dynamic-routing-of-llm-experts-fo/","scores":{"empirical_rigor":6,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes MM-DREX, a multimodal-driven, dynamically routed expert framework based on large language models for financial trading.","quote":"we propose MM-DREX: a Multimodal-driven, Dynamically-Routed EXpert framework based on large language models.","summary":"The inherent non-stationarity of financial markets and the complexity of multi-modal information pose significant challenges to existing quantitative trading models. Traditional methods relying on fixed structures and unimodal data struggle to adapt to market regime shifts, while large language…","strategy":"MM-DREX"},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"multimodal financial dataset","provider":"Yahoo Finance and partnering brokerage firms","kind":"market-prices","access":"public","period":null,"universe":"U.S. equities, Chinese A-shares, ETFs, cryptocurrencies, futures","quote":"dataset ... spans five major markets—U.S. equities, Chinese A-shares, ETFs, cryptocurrencies, and futures","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The raw OHLCV series for securities are obtained from Yahoo Finance and other partnering brokerage firms.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":"multiple assets across equities, futures, crypto","asset_class":"multi-asset","frequency":null},"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":true},"card_detail":null,"card_quote":"Many existing models also employ binary “all-in” or “all-out” strategies, leading to excessive trading costs and heightened volatility exposure.","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Dynamic routing achieves a total return of 25.75% and Sharpe ratio of 1.63, outperforming static strategies.","kind":"performance","quote":"The results demonstrate that dynamic routing significantly outperforms all static strategies with a total return of 25.75% and Sharpe ratio of 1.63."},{"finding":"Uniform weighting results in a maximum drawdown of 21.45%, a 45.3% increase compared to dynamic routing.","kind":"performance","quote":"... results in a maximum drawdown of 21.45%, representing a 45.3% increase compared to dynamic routing"},{"finding":"MM-DREX significantly outperforms 15 baselines across total return, Sharpe ratio, and maximum drawdown.","kind":"performance","quote":"MM-DREX significantly outperforms 15 baselines (including state-of-the-art financial LLMs and deep reinforcement learning models) across key metrics: total return, Sharpe ratio, and maximum drawdown"}],"reported_performance":{"strategy":"MM-DREX","sharpe":2.15,"sharpe_benchmark":0.75,"annual_return_pct":null,"total_return_pct":47.5,"max_drawdown_pct":14.76},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":24,"citations":{"cited_by_in_corpus":3,"by_independent_authors":3,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":1},"independent_papers":[{"paper":{"paper_id":"2601.22162","title":"UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videos","paper_date":"2026-01-09","authors":["Zhi Yang","Lingfeng Zeng","Fangqi Lou","Qi Qi","Wei Zhang","Zhenyu Wu"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/unifineval-towards-unified-evaluation-of-financial-multimodal-models-across/"},"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":1,"extracted_at":"2026-11-14T17:27:47Z"},"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/"}