arXiv cs.CL· Fengyuan Liu, Yuchen Fu, Yuqi Wang, Fengyuan Liu, Mukai Li, Qi Liu·· 2 天前AI 评分27
X-Alpha：具备记忆驱动自进化能力的 AI 量化研究员
X-Alpha: An AI Quant Researcher with Memory-Driven Self-Evolution
AI 导读
X-Alpha 是一个将持久研究记忆与假设到代码的持续发现相结合的 AI 量化研究员，通过 Report-to-Memory Abstraction（RMA）把金融报告转化为可执行的研究路径，并借助记忆驱动路由重定向探索。它在中国大陆、美国和中国香港的五个股票指数上评估，以 CSI300 为核心的实验显示其因子质量与信号多样性优于基线，并在多个市场和预测周期上取得一致的生成级增益。
正文 · 原文
Abstract:Human quantitative researchers mine alpha through an iterative process: they derive hypotheses from financial knowledge, implement and test them as factors, and use the resulting evidence to guide subsequent research. Yet automated alpha mining faces three key bottlenecks: noisy financial knowledge is not directly actionable, exploration can remain confined to similar mechanisms, and feedback may remain tied to individual mining runs. To address these bottlenecks, we introduce X-Alpha, an AI Quant Researcher that couples persistent research memory with continuous hypothesis-to-code discovery. Report-to-Memory Abstraction (RMA) uses a multi-layer filtering-and-abstraction process to convert financial reports into actionable, data-compatible research paths. Memory-driven routing uses accumulated experience to redirect exploration and define a targeted search space for each cycle. Within each cycle, hypotheses are implemented as executable factors and refined through empirical validation and code-based evolution. Empirical outcomes are consolidated into persistent research memory to guide subsequent exploration, enabling memory-driven self-evolution across cycles. We evaluate X-Alpha on five equity indices spanning mainland China, the United States, and Hong Kong, with comprehensive experiments centered on CSI300. Experiments show strong alpha discovery performance against baselines, with improvements in factor quality and signal diversity and consistent generation-level gains across multiple markets and prediction horizons.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2607.08332 [cs.CL] |
| (or arXiv:2607.08332v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.08332 arXiv-issued DOI via DataCite |
Submission history
From: Fengyuan Liu [view email]
[v1]
Thu, 9 Jul 2026 10:17:22 UTC (1,637 KB)
[v2]
Mon, 13 Jul 2026 07:04:03 UTC (1,860 KB)
[v3]
Thu, 15 Oct 2026 08:12:52 UTC (1,060 KB)
来源：arXiv cs.CL · arxiv.org