发表机构
HKUST(GZ); Paradoox AI Research（香港科技大学（广州）; 悖论人工智能研究）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对量化策略优化多依赖人工且易出错的问题，提出EVOQUANT框架，利用大语言模型诊断瓶颈、生成候选编辑，经多阶段验证选最佳策略，能提炼经验持续改进，实验表明该方法有效提升夏普比率，为金融策略研究提供新途径。
AI 中文摘要
量化策略优化很大程度上仍依赖人工，需要领域专家识别微弱信号、调整风险控制规则并反复验证迭代修正。大语言模型虽能加速此过程，但直接依赖其重写交易策略常导致幻觉编辑、策略漂移和回测过度拟合。我们提出EVOQUANT，一种用于量化交易策略优化的自进化验证器引导框架。该方法利用大语言模型深度诊断性能瓶颈，生成语义受控的候选编辑，通过多阶段验证管道选择最佳策略，并将优化经验提炼为可复用知识以持续自我改进。我们用七种代表性策略评估方法，包括四种A股市场策略和三种加密市场策略。实验结果表明，我们的方法显著提高了所有测试策略的夏普比率：平均测试夏普比率从-0.298提高到0.538，最佳策略实现了199%的相对提升。消融研究和更严格条件下的压力测试进一步验证了框架的有效性和稳健性。总体而言，这项工作将量化策略优化从成本高昂的手动试错转变为自动化且可验证的迭代范式，为将大语言模型应用于金融策略研究开辟了新路径。
英文摘要
Quantitative strategy optimization remains largely manual, requiring domain experts to identify weak signals, tune risk-control rules, and repeatedly validate iterative revisions. Large language models can accelerate this process, but directly relying on them to rewrite trading strategies often introduces hallucinated edits, strategy drift, and backtest overfitting. We propose EVOQUANT, a self-Evolving Verifier-guided framework for strategy Optimization in Quantitative trading. Our method utilizes LLMs to deeply diagnose performance bottlenecks, generates semantically controlled candidate edits, selects the best strategy through a multi-stage verification pipeline, and distills optimization experience into reusable knowledge for continual self-improvement. We evaluate our method using seven representative strategies: four from the A-share market and three from the Crypto market. Experimental results show that our method significantly improves the Sharpe ratio across all tested strategies: the average test Sharpe increases from -0.298 to 0.538, and the best-performing strategy achieves a 199% relative improvement. Ablation studies and stress tests under stricter conditions further validate the effectiveness and robustness of the framework. Overall, this work transforms quantitative strategy optimization from costly manual trial and error into an automated and verifiable iterative paradigm, offering a new path for applying large language models to financial strategy research.
Comments13 pages, 6 figures, 3 tables
