{"paper_id":"2609.33524","title":"EverMine: Dissecting the Self-Evolution of Research Capabilities in Long-Horizon Alpha Research","authors":["Siyuan Li","Jiangfeng Zhang","Rui Yao","Weihua Qiu","Mingyang Xu","Zixuan Yuan"],"paper_date":"2026-09-27","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2609.33524","page_url":"https://thequant.space/flowcharts/evermine-dissecting-the-self-evolution-of-research-capabilities-in-long-horizon/","scores":{"empirical_rigor":7,"math_complexity":6,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes EverMine, an empirical framework that separates research history, current factor portfolio, and reusable capabilities to study self‑evolving research in long‑horizon alpha discovery.","quote":"We introduce EverMine, an empirical framework for studying self-evolving research capabilities in long-horizon alpha discovery.","summary":"Self-evolving agents aim to turn research feedback into reusable skills, tools, and research rules. Whether these accumulated capabilities continue to improve later research requires controlled evaluation. Long-horizon alpha discovery provides a state-dependent setting: once a new factor enters the…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Research uses a point‑in‑time universe of 60 USDT‑denominated spot trading pairs selected by turnover, with no future information used.","type":"market","stated":"explicit","quote":"as the only raw market‑data source. The universe contains USDT‑denominated spot trading pairs, with all timestamps in UTC"},{"assumption":"All features, labels, and asset selection at time t use only information visible within the corresponding evaluation boundary.","type":"data","stated":"explicit","quote":"All processing follows one rule: asset selection, features, and labels at time t use only information visible within the corresponding evaluation boundary."},{"assumption":"The factor pool has a fixed capacity of 30 and follows a fixed update rule during the development period.","type":"model","stated":"explicit","quote":"The evaluator maintains a factor pool with capacity 30 under a fixed update rule and measures predictive"},{"assumption":"Research runs are resource‑matched across conditions, ensuring comparable computational and evaluation budgets.","type":"other","stated":"explicit","quote":"Under matched resource limits, we compare complete research runs with either fixed or continuously evolving Cap."}]},"datasets":{"status":"available","items":[{"name":"Binance Spot dynamic‑U60 dataset","provider":"Binance Data Vision archive","kind":"market-prices","access":"public","period":"2025-01-01 to 2025-12-31 (development), ","universe":"Top 60 USDT spot trading pairs by turnover each month","quote":"as the only raw market‑data source… The universe contains USDT‑denominated spot trading pairs","known_id":"binance"}],"known":[{"id":"binance","name":"Binance","provider":"Binance","kind":"market-prices","access":"public","quote":"We use the public Binance Data Vision archive of spot-market klines1 as the only raw market-data source.","mentions":3,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"Across 18 long‑horizon trajectories and 48 continuation branches, there is no consistent improvement from explicit capability evolution.","kind":"negative","quote":"Across 18 long‑horizon trajectories, end‑to‑end comparisons show no consistent gain from Cap evolution"},{"finding":"Parameter tuning of existing factor structures yields a positive net improvement in 16 of 18 trajectories.","kind":"performance","quote":"Parameter tuning of existing factor structures contributes a positive net improvement in 16 of 18 trajectories, showing that familiar structures can remain useful targets for further research."},{"finding":"Submitting all screened‑out candidates sequentially slightly lowers the final portfolio IC in both replayed batches.","kind":"negative","quote":"After all screened‑out factors are sequentially submitted, the final portfolio IC decreases slightly in both batches."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":9,"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":"2026-11-14T17:04:29Z"},"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/"}