AlgoEvolve: LLM-driven Meta-evolution of Algorithmic Trading Programs

AlgoEvolve：基于大语言模型的算法交易程序元进化

Abstract: Recent work shows that Large Language Models (LLMs) can act as semantic mutation operators for the evolutionary discovery of programs and proofs. Most current applications focus on static coding benchmarks. We extend this paradigm to algorithmic trading. This domain is uniquely challenging because it is noisy, non-stationary, and highly discontinuous. 摘要： 近期研究表明，大语言模型（LLMs）可以作为语义变异算子，用于程序和证明的进化式发现。目前大多数应用集中在静态编码基准测试上。我们将这一范式扩展到了算法交易领域。该领域极具挑战性，因为它具有噪声大、非平稳且高度不连续的特点。

We present AlgoEvolve, an LLM-driven evolutionary framework that generates, evaluates, and iteratively improves executable trading strategies. These strategies are expressed as Python code and evaluated through a rigorous testing protocol. Across multiple experiments, the system exhibits emergent regime-adaptive strategy logic, including autonomous shifts in trading rules. 我们提出了 AlgoEvolve，这是一个由大语言模型驱动的进化框架，能够生成、评估并迭代改进可执行的交易策略。这些策略以 Python 代码形式呈现，并通过严格的测试协议进行评估。在多项实验中，该系统展现出了涌现的“市场环境自适应”策略逻辑，包括交易规则的自主转换。

We further introduce a meta-evolutionary outer loop that evolves the prompts guiding program synthesis in the inner loop. This outer loop discovers improved search heuristics. These heuristics balance exploration and exploitation while reducing zero-trade failures. They consistently outperform initial human-designed instructions. 我们进一步引入了一个元进化外循环，用于进化指导内循环程序合成的提示词（Prompts）。该外循环能够发现改进后的搜索启发式算法。这些启发式算法在平衡探索与利用的同时，减少了“零交易”失败的情况。它们的表现始终优于最初由人类设计的指令。

The results demonstrate that LLM-based semantic evolution provides a viable approach for continual program synthesis in complex environments. 研究结果表明，基于大语言模型的语义进化为复杂环境下的持续程序合成提供了一种可行的方法。