Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Zuoyou, Zhao, Li, Sun, Rui, Sun, Ruohan, Li, Zhongjian, Li, Jing, Jiang, Daxin, Bai, Zuo, Hua, Cheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909977767051264
author Jiang, Zuoyou
Zhao, Li
Sun, Rui
Sun, Ruohan
Li, Zhongjian
Li, Jing
Jiang, Daxin
Bai, Zuo
Hua, Cheng
author_facet Jiang, Zuoyou
Zhao, Li
Sun, Rui
Sun, Ruohan
Li, Zhongjian
Li, Jing
Jiang, Daxin
Bai, Zuo
Hua, Cheng
contents Signal decay and regime shifts pose recurring challenges for data-driven investment strategies in non-stationary markets. Conventional time-series and machine learning approaches, which rely primarily on historical correlations, often struggle to generalize when the economic environment changes. While large language models (LLMs) offer strong capabilities for processing unstructured information, their potential to support quantitative factor screening through explicit economic reasoning remains underexplored. Existing factor-based methods typically reduce alphas to numerical time series, overlooking the semantic rationale that determines when a factor is economically relevant. We propose Alpha-R1, an 8B-parameter reasoning model trained via reinforcement learning for context-aware alpha screening. Alpha-R1 reasons over factor logic and real-time news to evaluate alpha relevance under changing market conditions, selectively activating or deactivating factors based on contextual consistency. Empirical results across multiple asset pools show that Alpha-R1 consistently outperforms benchmark strategies and exhibits improved robustness to alpha decay. The full implementation and resources are available at https://github.com/FinStep-AI/Alpha-R1.
format Preprint
id arxiv_https___arxiv_org_abs_2512_23515
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning
Jiang, Zuoyou
Zhao, Li
Sun, Rui
Sun, Ruohan
Li, Zhongjian
Li, Jing
Jiang, Daxin
Bai, Zuo
Hua, Cheng
Trading and Market Microstructure
Artificial Intelligence
Computational Engineering, Finance, and Science
Machine Learning
Signal decay and regime shifts pose recurring challenges for data-driven investment strategies in non-stationary markets. Conventional time-series and machine learning approaches, which rely primarily on historical correlations, often struggle to generalize when the economic environment changes. While large language models (LLMs) offer strong capabilities for processing unstructured information, their potential to support quantitative factor screening through explicit economic reasoning remains underexplored. Existing factor-based methods typically reduce alphas to numerical time series, overlooking the semantic rationale that determines when a factor is economically relevant. We propose Alpha-R1, an 8B-parameter reasoning model trained via reinforcement learning for context-aware alpha screening. Alpha-R1 reasons over factor logic and real-time news to evaluate alpha relevance under changing market conditions, selectively activating or deactivating factors based on contextual consistency. Empirical results across multiple asset pools show that Alpha-R1 consistently outperforms benchmark strategies and exhibits improved robustness to alpha decay. The full implementation and resources are available at https://github.com/FinStep-AI/Alpha-R1.
title Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning
topic Trading and Market Microstructure
Artificial Intelligence
Computational Engineering, Finance, and Science
Machine Learning
url https://arxiv.org/abs/2512.23515