让金融因子挖掘智能体学会从失败中总结规律，避免重复踩坑。
AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents
- 记录因子修改模式的成败上下文，而非只存结果或完整路径。
- 在沪深300和标普500上提升固定预算下的因子发现效率。
- 适合需要持续优化、避免重复试错的量化研究者使用。
大模型智能体在金融因子挖掘中展现出潜力，结合财务先验、符号推理、可执行因子生成及反馈驱动优化。然而，其面临组合搜索空间大、反馈噪声强且非平稳、重复发现与过拟合风险等问题。为此，我们提出AlphaMemo，一种具备结构化搜索过程记忆的自演化因子挖掘智能体。不同于仅记忆最终因子或完整轨迹，AlphaMemo记录特定父因子背景下哪些修改模式有效或无效。通过提取抽象语法树（AST）差异中的模式，采用置信度门控残差记忆机制，并结合非对称否决控制抑制高置信度失败模式。在沪深300与标普500上的实验显示，该方法提升了样本外表现与固定预算下的发现效率；消融实验验证了残差学习、置信度门控、AST差异模式及否决记忆的关键作用。代码已开源。
原文摘要 · Abstract (English)
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 https://github.com/jarrettyu/AlphaMemo.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。