AQuA：递归自我改进的量化交易研究智能体

中文摘要 AI 辅助

我们在量化投资研究层面研究递归自我改进，即自主系统能否利用早期实验的证据来改进后续迭代中提出的假设和候选方案。我们提出AQuA，它包含两个独立的、由大语言模型驱动的研究系统：一个用于符号因子发现，另一个用于可训练模型开发。这两个系统不共享智能体、记忆、候选空间或研究状态，而是各自通过保留已验证的证据并将其用于指导后续提议，独立完成自身的研究闭环。在这种受限的意义上，两个系统均在研究过程层面实现了递归自我改进。每个系统还使用自身的封闭沙箱，该沙箱固定了数据划分、特征与标签定义以及评估器，同时仅允许模型通过受限的因子表达式或配置差异进行操作。因子系统是一个由管理器介导的多智能体流水线，它发现并组合因子，形成的信号在加密资产 universe 上的组合信息系数约为0.190。模型系统是一个基于配置的混合时间序列架构循环，它在美股上实现了每股信息系数+0.0843，并将其转化为阈值多空策略，在双边成本下的留存夏普比率最高达+2.50，该策略在2021年至2025年的每一年均为正收益。

英文摘要

We study recursive self-improvement at the level of quantitative-investment research: whether an autonomous system can use evidence from earlier experiments to improve the hypotheses and candidates proposed in later iterations. We present AQuA, which comprises two separate language-model-driven research systems: one for symbolic factor discovery and one for trainable model development. Each system records experimental results and uses them to guide subsequent proposals. Each operates in a fixed sandbox, which fixes the data splits, feature and label definitions, and evaluator while allowing the model to act only through constrained factor expressions or configuration diffs. The factor system, a manager-mediated multi-agent pipeline, discovers and combines factors into a signal that reaches a combined validation information coefficient of about $0.190$ on a crypto universe. The model system, a config-driven loop over a hybrid time-series architecture, reaches a per-stock information coefficient of $+0.0843$ on US equities and converts it into a threshold long/short strategy with a held-out Sharpe of up to $+2.50$ at a two-leg cost. The strategy is positive in every year from 2021 to 2025.

发表机构

• Princeton University（普林斯顿大学）
• Ant Group（蚂蚁集团）
• Stanford University（斯坦福大学）

机构由 AI 辅助整理，请以论文原文为准。