{"paper_id":"2505.15155","title":"R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization","authors":["Yuante Li","Xu Yang","Xiao Yang","Minrui Xu","Xisen Wang","Weiqing Liu","Jiang Bian"],"paper_date":"2025-05-21","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2505.15155v2","page_url":"https://thequant.space/flowcharts/rd-agent-quant-a-multi-agent-framework-for-data-centric-fa/","scores":{"empirical_rigor":8,"math_complexity":4.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes R&D-Agent(Q), a data‑centric multi‑agent framework that automates full‑stack quantitative strategy research and development via coordinated factor‑model co‑optimization.","quote":"we propose R&D-Agent for Quantitative Finance, in short RD-Agent(Q), the first data-centric multi-agent framework designed to automate the full-stack research and development of quantitative strategies via coordinated factor-model co-optimization.","summary":"Financial markets pose fundamental challenges for asset return prediction due to their high dimensionality, non-stationarity, and persistent volatility. Despite advances in large language models and multi-agent systems, current quantitative research pipelines suffer from limited automation, weak…","strategy":"R&D-Agent(Q)"},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"CSI 300 dataset","provider":null,"kind":"market-prices","access":"public","period":"2008-01-01 to 2020-08-01","universe":"300 large‑cap A‑share stocks in the Chinese market","quote":"we use the CSI 300 dataset, covering 300 large-cap A-share stocks in the Chinese market. The time span is split into training (Jan 1, 2008 – Dec 31, 2014), validation (Jan 1, 2015 – Dec 31, 2016), and testing (Jan 1, 2017 – Aug 1, 2020)."}],"known":[{"id":"kaggle","name":"Kaggle","provider":"Kaggle","kind":"other","access":"public","quote":"D.6 Real-World Quantitative Competition Analysis To further explore the potentials of R&D-Agent(Q) frameworks, we utilize R&D-Agent(Q) for the Optiver Realized Volatility Prediction [77] competition on Kaggle.","mentions":1,"used_in":1},{"id":"wind","name":"Wind","provider":"Wind Information","kind":"market-prices","access":"commercial","quote":"These fields can be obtained by searching their names in the Wind terminal (https://www.wind.com.cn/mobile/ WFT/en.html).","mentions":1,"used_in":1}],"sample":{"start":"2024","end":"2025-06","market":"CSI 500","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"cost under $10 total for the reported results","quote":"at a cost under $10, R&D-Agent(Q) achieves approximately 2× higher ARR","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"cost under $10 total for the reported results","card_quote":"at a cost under $10, R&D-Agent(Q) achieves approximately 2× higher ARR","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"R&D-Agent(Q) achieves up to 2× higher annualized returns than classical factor libraries while using 70% fewer factors.","kind":"performance","quote":"RD-Agent(Q) achieves up to 2X higher annualized returns than classical factor libraries using 70% fewer factors"},{"finding":"The framework outperforms state‑of‑the‑art deep time‑series models on real markets.","kind":"performance","quote":"outperforms state-of-the-art deep time-series models on real markets"},{"finding":"Joint factor‑model optimization delivers an excellent trade‑off between predictive accuracy and strategy robustness.","kind":"performance","quote":"its alternating factor–model optimization further delivers excellent trade‑off between predictive accuracy and strategy robustness"}],"reported_performance":{"strategy":"R&D-Agent(Q)","sharpe":2.1721,"sharpe_benchmark":null,"annual_return_pct":19.82,"total_return_pct":null,"max_drawdown_pct":6.56},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":21,"citations":{"cited_by_in_corpus":14,"by_independent_authors":13,"how_cited":{"used_as_baseline":2,"uses_method_or_data":3,"extends":0,"discusses_findings":0,"mentions":6,"unclassified":3},"independent_papers":[{"paper":{"paper_id":"2611.19937","title":"AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data","paper_date":"2026-11-15","authors":["Annan Wang","Yuchen Xie","Yu Cen","Leon Liangyu Chen","Qianyu Julie Zhu","Xin Li"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/allocflow-end-to-end-portfolio-trading-action-generation-from-raw-market-data/"},"how":"used_as_baseline","quote":null},{"paper":{"paper_id":"2603.20247","title":"AlphaLogics: A Market Logic-Driven Multi-Agent System for Scalable and Interpretable Alpha Factor Generation","paper_date":"2026-03-10","authors":["Zhangyuhua Weng","Shengli Zhang","Taotao Wang","Yihan Xia"],"empirical_rigor":7.5,"page_url":"https://thequant.space/flowcharts/alphalogics-a-market-logic-driven-multi-agent-system-for-scalable-and/"},"how":"used_as_baseline","quote":null},{"paper":{"paper_id":"2610.06947","title":"FactorBench: A Portfolio-Aware Benchmark for Automated Factor Mining","paper_date":"2026-10-03","authors":["Zhuohan Wang","Carmine Ventre"],"empirical_rigor":9,"page_url":"https://thequant.space/flowcharts/factorbench-a-portfolio-aware-benchmark-for-automated-factor-mining/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2512.23515","title":"Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning","paper_date":"2025-12-29","authors":["Zuoyou Jiang","Li Zhao","Rui Sun","Ruohan Sun","Zhongjian Li","Jing Li"],"empirical_rigor":8.5,"page_url":"https://thequant.space/flowcharts/alpha-r1-alpha-screening-with-llm-reasoning-via-reinforceme/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2602.07085","title":"QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining","paper_date":"2026-02-06","authors":["Jun Han","Shuo Zhang","Wei Li","Zhi Yang","Yifan Dong","Tu Hu"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/quantaalpha-an-evolutionary-framework-for-llm-driven-alpha-mining/"},"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":true,"code_url":"https://github.com/microsoft/RD-Agent","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":"2026-11-14T17:37:20Z"},"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/"}