{"paper_id":"2611.25732","title":"Auto-Alpha: A Framework for Autonomous Factor Research","authors":["Hui Cai","Kangcheng Deng","Tianyi Ma","Qixuan Yang","Jiacheng Lu","Rui Sun","Beidi Luan","Jing Li","Zuo Bai"],"paper_date":"2026-11-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2611.25732","page_url":"https://thequant.space/flowcharts/auto-alpha-a-framework-for-autonomous-factor-research/","scores":{"empirical_rigor":6,"math_complexity":5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes Auto-Alpha, a framework that connects report‑guided initialization to self‑directed factor research through a test‑driven implementation loop.","quote":"We present Auto-Alpha, a framework that connects report-guided initialization to self-directed research through a test-driven implementation loop.","summary":"Autonomous factor research requires generating economic hypotheses as well as implementing and testing them. We present Auto-Alpha, a framework that connects report-guided initialization to self-directed research through a test-driven implementation loop. An idea agent proposes economic mechanisms…","strategy":"weekly Top-300 portfolio"},"assumptions":{"status":"available","items":[{"assumption":"Trades are executed using VWAP and the account is marked at the close.","type":"execution","stated":"implied","quote":"Trades use VWAP and the account is marked at the close.","support":"full"},{"assumption":"The execution model does not estimate market impact or impose a volume‑participation cap.","type":"execution","stated":"implied","quote":"This execution model does not estimate market impact or impose a volume-participation cap.","support":"full"},{"assumption":"Constant transaction fees of 1 bp for buys and 6 bp for sells (plus minimum RMB 5 and 10 bp slippage per side) are applied throughout the period.","type":"model","stated":"implied","quote":"Constant fees throughout the period are 1 basis point for buys and 6 for sells, with a RMB 5 minimum per stock and direction; proportional slippage adds 10 basis points on each side.","support":"full"},{"assumption":"The eligible universe excludes ST stocks and stocks listed for fewer than 60 days.","type":"data","stated":"implied","quote":"The eligible Shanghai and Shenzhen A-share universe excludes ST stocks and stocks listed for fewer than 60 days; actual fills respect the engine’s suspension, price-limit, and approximate lot-size rules.","support":"full"},{"assumption":"No additional turnover or stock‑replacement limit is imposed.","type":"execution","stated":"implied","quote":"No additional turnover or stock-replacement limit is imposed.","support":"full"},{"assumption":"Weekly rebalancing uses the first trading day of each week to generate a Top‑300 target executed the next day.","type":"execution","stated":"implied","quote":"Each week’s first trading day produces a new Top-300 target for execution on the next trading day.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"Shanghai and Shenzhen A‑share price data","provider":null,"kind":"market-prices","access":"unknown","period":"2020–2026","universe":"A‑share universe (excluding ST stocks and newly listed stocks)","quote":"The account runs from the first trading day of 2020 through 2026-11-03. The eligible Shanghai and Shenzhen A-share universe excludes ST stocks and stocks listed for fewer than 60 days; actual fills respect the engine’s suspension, price-limit, and approximate lot-size rules.","support":"full"},{"name":"CSI 1000 price index","provider":null,"kind":"benchmark","access":"unknown","period":null,"universe":null,"quote":"CSI 1000 (000852.SH) is the reference benchmark, with no index hedge or constraint restricting selection to its constituents. The net portfolio returns 16.81% annualized, compared with 1.71% for the CSI 1000 price index.","support":"full"}],"known":[],"sample":{"start":"2020-01","end":"2026-11","market":"Shanghai and Shenzhen A-share universe","asset_class":"equities","frequency":"weekly"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"Constant fees of 1 bp for buys and 6 bp for sells (minimum RMB 5 per stock) plus proportional slippage of 10 bp on each side.","quote":"Constant fees throughout the period are 1 basis point for buys and 6 for sells, with a RMB 5 minimum per stock and direction; proportional slippage adds 10 basis points on each side.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Constant fees of 1 bp for buys and 6 bp for sells (minimum RMB 5 per stock) plus proportional slippage of 10 bp on each side.","card_quote":"Constant fees throughout the period are 1 basis point for buys and 6 for sells, with a RMB 5 minimum per stock and direction; proportional slippage adds 10 basis points on each side.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The median 1‑day Rank IC of the 105‑factor library is 0.0301.","kind":"predictive-accuracy","quote":"The median 1-day Rank IC is 0.0301, and a weekly Top-300 portfolio returns 16.81% annualized after stated costs over 2020-2026, versus 1.71% for the CSI 1000 price index. Its median 1-day Rank IC is 0.0301.","support":"partial"},{"finding":"A weekly Top‑300 portfolio constructed from the library returns 16.81% annualized after stated costs over 2020‑2026, versus 1.71% for the CSI 1000 benchmark.","kind":"performance","quote":"The median 1-day Rank IC is 0.0301, and a weekly Top-300 portfolio returns 16.81% annualized after stated costs over 2020-2026, versus 1.71% for the CSI 1000 price index. The net portfolio returns 16.81% annualized, compared with 1.71% for the CSI 1000 price index.","support":"full"},{"finding":"The portfolio’s Sharpe ratio is 0.763 and its maximum drawdown is 32.16%.","kind":"performance","quote":"Its Sharpe ratio is 0.763, with a maximum drawdown of 32.16%.","support":"full"},{"finding":"Annualized one‑way turnover of the portfolio is 19.15 times account value.","kind":"performance","quote":"Annualized one-way turnover is 19.15 times account value.","support":"full"}],"reported_performance":{"strategy":"weekly Top-300 portfolio","sharpe":0.763,"sharpe_benchmark":null,"annual_return_pct":16.81,"total_return_pct":null,"max_drawdown_pct":32.16},"out_of_sample":{"method":"none","headline_out_of_sample":false}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":22,"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":3,"extracted_at":"2026-11-20T11:38:37Z"},"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/"}