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

• URL: http://arxiv.org/abs/2512.23515v1
• Date: Mon, 29 Dec 2025 14:50:23 GMT
• Title: Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning
• Authors: Zuoyou Jiang, Li Zhao, Rui Sun, Ruohan Sun, Zhongjian Li, Jing Li, Daxin Jiang, Zuo Bai, Cheng Hua,
• Abstract summary: Signal decay and regime shifts pose recurring challenges for data-driven investment strategies in non-stationary markets.<n>Existing factor-based methods typically reduce alphas to numerical time series, overlooking the semantic rationale that determines when a factor is economically relevant.<n>We propose Alpha-R1, an 8B- parameter reasoning model trained via reinforcement learning for context-aware alpha screening.
• Score: 28.326583684637853
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns [51.02752099869218]
  Large Language Models (LLMs) display strikingly different generalization behaviors.<n>We introduce a novel benchmark that decomposes reasoning into atomic core skills.<n>We show that RL-tuned models maintain more stable behavioral profiles and resist collapse in reasoning skills, whereas SFT models exhibit sharper drift and overfit to surface patterns.
  arXiv  Detail & Related papers  (2025-12-30T08:16:20Z)
• Making Mathematical Reasoning Adaptive [61.45161826629692]
  We propose the AdaR framework to enable adaptive reasoning in large language models (LLMs)<n>AdaR synthesizes logically equivalent queries by varying variable values, and trains models with RLVR on these data to penalize spurious logic.<n> Experimental results demonstrate that AdaR improves robustness and generalization, achieving substantial improvement in mathematical reasoning.
  arXiv  Detail & Related papers  (2025-10-06T09:30:05Z)
• AlphaEval: A Comprehensive and Efficient Evaluation Framework for Formula Alpha Mining [6.167227740097627]
  Formula alpha mining, which generates predictive signals from financial data, is critical for quantitative investment.<n>Existing evaluation metrics predominantly include backtesting and correlation-based measures.<n>We propose AlphaEval, a unified, parallelizable, and backtest-free evaluation framework for automated alpha mining models.
  arXiv  Detail & Related papers  (2025-08-10T11:19:24Z)
• Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training [121.5858973157225]
  We investigate the effects of prolonged reinforcement learning on a small language model across a diverse set of reasoning domains.<n>We introduce controlled KL regularization, clipping ratio, and periodic reference policy resets as critical components for unlocking long-term performance gains.<n>Our model achieves significant improvements over strong baselines, including +14.7% on math, +13.9% on coding, and +54.8% on logic puzzle tasks.
  arXiv  Detail & Related papers  (2025-07-16T17:59:24Z)
• SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning [95.28059121743831]
  Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for training large language models (LLMs) on complex reasoning tasks.<n>We introduce a Self-aware Weakness-driven problem Synthesis framework (SwS) that systematically identifies model deficiencies and leverages them for problem augmentation.<n>SwS enables robust generalization byempowering the model to self-identify and address its weaknesses in RL, yielding average performance gains of 10.0% and 7.7% on 7B and 32B models.
  arXiv  Detail & Related papers  (2025-06-10T17:02:00Z)
• Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards [67.86091419220816]
  Large Language Models (LLMs) show great promise in complex reasoning.<n>A prevalent issue is superficial self-reflection'', where models fail to robustly verify their own outputs.<n>We introduce RISE (Reinforcing Reasoning with Self-Verification), a novel online RL framework designed to tackle this.
  arXiv  Detail & Related papers  (2025-05-19T17:59:31Z)
• AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay [43.50447460231601]
  We propose AlphaAgent, an autonomous framework that integrates Large Language Models with ad hoc regularizations for mining decay-resistant alpha factors.<n>AlphaAgent consistently delivers significant alpha in Chinese CSI 500 and US S&P 500 markets over the past four years.<n> Notably, AlphaAgent showcases remarkable resistance to alpha decay, elevating the potential for yielding powerful factors.
  arXiv  Detail & Related papers  (2025-02-24T02:56:46Z)
• QuantFactor REINFORCE: Mining Steady Formulaic Alpha Factors with Variance-bounded REINFORCE [5.560011325936085]
  Powerful deep learning methods for alpha factor mining lack interpretability, making them unacceptable in the risk-sensitive real markets.<n>Formulaic alpha factors are preferred for their interpretability, while the search space is complex and powerful explorative methods are urged.<n>Recently, a promising framework is proposed for generating alpha factors using deep reinforcement learning.
  arXiv  Detail & Related papers  (2024-09-08T15:57:58Z)
• AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors [14.80394452270726]
  This paper proposes a two-stage alpha generating framework AlphaForge, for alpha factor mining and factor combination.<n> Experiments conducted on real-world datasets demonstrate that our proposed model outperforms contemporary benchmarks in formulaic alpha factor mining.
  arXiv  Detail & Related papers  (2024-06-26T14:34:37Z)
• Synergistic Formulaic Alpha Generation for Quantitative Trading based on Reinforcement Learning [1.3194391758295114]
  This paper proposes a method to enhance existing alpha factor mining approaches by expanding a search space. We employ information coefficient (IC) and rank information coefficient (Rank IC) as performance evaluation metrics for the model.
  arXiv  Detail & Related papers  (2024-01-05T08:49:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.