{"paper_id":"2510.21147","title":"Hierarchical AI Multi-Agent Fundamental Investing: Evidence from China's A-Share Market","authors":["Chujun He","Zhonghao Huang","Xiangguo Li","Ye Luo","Kewei Ma","Yuxuan Xiong","Xiaowei Zhang","Mingyang Zhao"],"paper_date":"2025-10-24","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.21147v1","page_url":"https://thequant.space/flowcharts/hierarchical-ai-multi-agent-fundamental-investing-evidence/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a multi-agent AI-driven framework for fundamental equity investing that integrates macro, industry, and firm-level information to build optimized portfolios.","quote":"We present a multi-agent, AI-driven framework for fundamental investing that integrates macro indicators, industry-level and firm-specific information to construct optimized equity portfolios.","summary":"We present a multi-agent, AI-driven framework for fundamental investing that integrates macro indicators, industry-level and firm-specific information to construct optimized equity portfolios. The architecture comprises: (i) a Macro agent that dynamically screens and weights sectors based on…","strategy":"Hierarchical AI Multi-Agent Investing"},"assumptions":{"status":"available","items":[{"assumption":"Model parameters are trained on data from Jan 2019 to Dec 2023 and validated on Jan–Dec 2024, implying stationarity across the split.","type":"data","stated":"implied","quote":"model parameters are trained exclusively on the sample from January 2019 to December 2023, with performance validated on the out-of-sample period covering January to December 2024."},{"assumption":"The Risk Control agent can adjust portfolio positions in response to market volatility.","type":"model","stated":"implied","quote":"Risk Control agent that adjusts portfolio positions in response to market volatility."},{"assumption":"Reweighting of agent outputs occurs after sector context has been established, relying on hierarchical separation.","type":"model","stated":"implied","quote":"the hierarchical separation ensures that reweighting occurs after sector context has been established."},{"assumption":"LLM outputs are embedded within the hierarchical workflow rather than used as simple features.","type":"model","stated":"implied","quote":"Rather than treating LLM outputs generally as features, we embed them within the hierarchical workflow to allow them to compare with the structure signals in a dynamic way."},{"assumption":"The dataset of Chinese A‑share market constituents provides sufficient macro, industry, and firm‑level data for training and testing.","type":"data","stated":"implied","quote":"We evaluate the proposed framework using a comprehensive and challenging dataset comprising the Chinese A‑share market from January 1, 2019, to December 31, 2024"}]},"datasets":{"status":"available","items":[{"name":"Chinese A‑share market (CSI 300 constituents)","provider":null,"kind":"market-prices","access":"unknown","period":"2019-01-01 to 2024-12-31","universe":"CSI 300 Index constituents","quote":"We evaluate the system on the constituents by the CSI 300 Index of China’s A‑share market"},{"name":"Macro indicators (CPI, money supply, PMI)","provider":null,"kind":"macro","access":"unknown","period":null,"universe":null,"quote":"daily return and macro data including CPI, money supply and PMI, so the Macro agent facilitates comprehensive analysis in both macro and industrial perspectives."}],"known":[],"sample":{"start":"2024-01","end":"2024-12","market":"CSI 300 constituent stocks","asset_class":"equities","frequency":"daily"},"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":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"In the training period the framework achieved a cumulative return of 167.52%, Sharpe ratio 1.84, Sortino ratio 3.05 and Calmar ratio 1.42, outperforming benchmarks.","kind":"performance","quote":"It achieves a cumulative return (CR) of 167.52%, a Sharpe ratio (SR) of 1.84, a Sortino ratio of 3.05, and a Calmar ratio of 1.42."},{"finding":"In the out‑of‑sample testing period the model delivered a cumulative return of 55.41%, Sharpe 1.96, Sortino 3.72 and Calmar 4.43, beating standard benchmarks and non‑hierarchical multi‑agent baselines.","kind":"performance","quote":"Ours 55.41 55.41 28.20 14.90 1.96 3.72 -12.52 4.43"}],"reported_performance":{"strategy":"Hierarchical AI Multi-Agent Investing","sharpe":1.96,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":55.41,"max_drawdown_pct":12.52},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":21,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"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":"2026-11-14T17:23:41Z"},"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/"}