From Flat to Hierarchical: Evolving Tree-structured Thoughts for Fine-grained Alpha Mining
For quantitative finance researchers, TreEvo addresses the positional bias and search inefficiency in LLM-based alpha mining, offering a more efficient and effective approach.
TreEvo introduces tree-structured thought evolution for alpha mining, achieving competitive results with traditional methods in up to 200x fewer evaluations and outperforming LLM-driven EAs by 14.31% on average across four real-market datasets.
Alpha mining, aimed at discovering predictive return signals, is typically formulated as symbolic regression. Traditional symbolic methods suffer from search inefficiency and biased prior knowledge. Recently, Large Language Models (LLMs) have emerged as a promising alternative, automatically generating textual thoughts and executable codes to achieve both efficient and interpretable alpha mining. However, existing approaches mostly focus on leveraging LLM's reasoning and reflection capabilities, yet largely neglect the positional bias due to the flat thought representation which restricts efficiency and diversity of the search process. This paper introduces Tree-structured thought Evolution (TreEvo), which evolves hierarchically decomposed thoughts to expand the effective search space. In addition, we propose a set of evolutionary operators tailored to structured thoughts. Experiments on four real-market datasets demonstrate that TreEvo not only obtains competitive alphas with traditional methods in up to 200 times fewer evaluations, but also consistently outperforms LLM-driven EAs across all datasets by $14.31\%$ on average.