arXiv cs.AI· Hang Yu, Zifan Zheng, Chun Gan, Jeff Z. Pan, Tongliang Liu, Zhiyong Wang, Fengxiang He·· 3 小时前AI 评分37
AlphaMemo：面向自进化 Alpha 挖掘智能体的结构化搜索过程记忆
AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents
AI 导读
研究者提出 AlphaMemo，一个具备结构化搜索过程记忆的自进化 Alpha 挖掘智能体，用于解决 LLM 智能体在因子挖掘中面临的组合搜索空间、噪声反馈、重复发现与过拟合问题。该方法通过 AST 差异提取可复用编辑模式，结合置信度门控残差记忆与非对称否决控制抑制高置信失败模式。在 CSI 500 和 S&P 500 上的实验显示样本外表现与固定预算发现效率均有提升。
正文 · 原文
Abstract:LLM agents are promising for alpha mining via combining financial priors, symbolic reasoning, executable factor generation, and feedback-driven refinement. Yet, they face a combinatorial search space, noisy non-stationary feedback, redundant discoveries, and overfitting risks from naively reusing past successes. To address these challenges, we propose AlphaMemo, a self-evolving alpha mining agent with Structured Search-Process Memory. Rather than memorizing only final factors or full trajectories, AlphaMemo records reusable evidence about which edit motifs work or fail under specific parent-factor contexts. It extracts motifs from Abstract Syntax Tree (AST) differences, applies confidence-gated residual memory on top of a search-ledger prior, and uses asymmetric veto control to suppress high-confidence failure patterns. Experiments on CSI 500 and S&P 500 show improved out-of-sample performance and fixed-budget discovery efficiency, with ablations validating the roles of residual learning, confidence gating, AST-diff motifs, and veto memory. Code is at this https URL.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2606.20625 [cs.AI] |
| (or arXiv:2606.20625v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.20625 arXiv-issued DOI via DataCite |
Submission history
From: Fengxiang He [view email]
[v1]
Tue, 26 May 2026 15:48:09 UTC (340 KB)
[v2]
Thu, 22 Oct 2026 18:14:45 UTC (361 KB)
来源：arXiv cs.AI · arxiv.org