From Flat to Hierarchical: Evolving Tree-structured Thoughts for Fine-grained Alpha Mining

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ren, Junji, Zhao, Junjie, Liu, Shengcai, Yang, Peng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911737226199040
author Ren, Junji
Zhao, Junjie
Liu, Shengcai
Yang, Peng
author_facet Ren, Junji
Zhao, Junjie
Liu, Shengcai
Yang, Peng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16334
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Flat to Hierarchical: Evolving Tree-structured Thoughts for Fine-grained Alpha Mining
Ren, Junji
Zhao, Junjie
Liu, Shengcai
Yang, Peng
Computational Engineering, Finance, and Science
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.
title From Flat to Hierarchical: Evolving Tree-structured Thoughts for Fine-grained Alpha Mining
topic Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2508.16334