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

TL;DR

Alpha-R1 leverages large language models and reinforcement learning to improve alpha screening by incorporating economic reasoning and real-time news analysis, enhancing robustness in non-stationary markets.

Contribution

This work introduces Alpha-R1, a novel reasoning model that uses reinforcement learning with LLMs for context-aware alpha screening based on economic logic and news.

Findings

Outperforms benchmark strategies in multiple asset pools

Demonstrates improved robustness to alpha decay

Utilizes real-time news for dynamic factor relevance

Abstract

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.