From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery

Modern quantitative trading increasingly relies on systematic models to extract predictive signals from large-scale financial data, where alpha factor discovery plays a central role in transforming market observations into tradable signals. Recent LLM-based methods have shown promise in automating factor generation, but most of them still rely on prompt-level generation--evaluation--feedback loops for iterative optimization. As the loop becomes longer, repeatedly appended historical candidates and feedback can cause context explosion, increase inference cost, dilute useful information, and introduce feedback drift. Moreover, these methods often depend on very large LLMs whose stable generation preferences may lead to structurally similar expressions, redundant candidates, and search stagnation. To address these limitations, we propose textscQuantEvolver, a self-evolving alpha factor discovery framework based on reinforcement fine-tuning. Instead of accumulating feedback in the prompt, textscQuantEvolver converts executable quantitative evaluation into policy updates, enabling a Miner LLM to internalize historical optimization experience through parameter learning. Specifically, textscQuantEvolver constructs high-quality seed factors, builds diverse seed--time-window training tasks, generates executable Factor DSL expressions, evaluates them through Regime Backtest, and optimizes the Miner LLM with Diversity-Complementarity Reward. During training, high-quality factors are continuously accumulated in a Mined Factor Database, which serves as the final discovered factor library. Extensive experiments on three realistic market benchmarks demonstrate the effectiveness of textscQuantEvolver, which consistently improves the primary evaluation metric of each task over existing LLM-based alpha factor discovery baselines, produces higher-quality and more complementary factor pools.