Newest papers

EverMine: Dissecting the Self-Evolution of Research Capabilities in Long-Horizon Alpha Research

Siyuan Li, Jiangfeng Zhang, Rui Yao, Weihua Qiu, Mingyang Xu, Zixuan Yuan · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2609.33524 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Penemuan alpha jangka panjang bertujuan untuk mengubah umpan balik penelitian menjadi keterampilan, alat, dan aturan penelitian yang dapat digunakan kembali. Apakah kemampuan yang terakumulasi ini terus meningkatkan penelitian selanjutnya membutuhkan evaluasi terkontrol. Penemuan alpha jangka panjang menyediakan pengaturan yang tergantung pada negara: setelah faktor baru memasuki portofolio, informasi prediktif sudah tercakup perubahan, sehingga nilai kandidat atau pengalaman yang sama dapat berubah seiring waktu. Kami memperkenalkan EverMine, kerangka empiris untuk mempelajari kemampuan penelitian yang berkembang sendiri dalam penemuan alpha jangka panjang. EverMine memecah penelitian ke dalam sejarah (Hist), portofolio faktor saat ini (Frontier), dan kemampuan yang dapat digunakan kembali pada waktu yang sama (Cap). Di bawah batas sumber daya yang cocok, kami membandingkan kinerja lengkap dengan Cap tetap atau berkembang, dan menggantikan pengujian nilai IC secara menyeluruh sementara mengeksplorasi status Hist

Machine translation (Meta M2M100); the English original follows.

Abstract

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 portfolio, the predictive information already covered changes, so the value of the same candidate or experience may change over time. We introduce EverMine, an empirical framework for studying self-evolving research capabilities in long-horizon alpha discovery. EverMine decomposes the research state into history (Hist), the current factor portfolio (Frontier), and reusable capabilities (Cap). Under matched resource limits, we compare complete runs with fixed or evolving Cap, and replace Cap while holding Hist and Frontier fixed to estimate the conditional value of accumulated capabilities. We also combine full trajectories with historical-state replay to examine how experience-based decisions affect candidate selection and portfolio outcomes. Across 18 long-horizon trajectories, end-to-end comparisons show no consistent gain from Cap evolution. Across 48 continuation branches from shared Hist and Frontier states, accumulated Cap also does not consistently outperform the initial Cap. Parameter tuning of existing factor structures can still improve the portfolio. In an exploratory replay of two screening batches from one Evolving trajectory, some screened-out candidates have positive marginal value at the original state, yet submitting all screened-out candidates sequentially slightly lowers final portfolio IC in both batches. These results show that candidate value depends on the evolving portfolio and submission order, and motivate evaluating self-evolving research capabilities through end-to-end outcomes, conditional capability value, and the consequences of experience-based decisions.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Portfolio, Computer science, Efficient frontier, Resource (disambiguation), Value (mathematics), Selection (genetic algorithm)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange