Abstract
Formulaic alpha discovery is a core challenge in quantitative trading, as identifying alphas that work well together remains difficult. Recent reinforcement learning (RL) methods formulate this task as a Markov decision process (MDP), but two important issues remain unresolved. First, as the alpha pool evolves, the reward function changes accordingly, making the MDP inherently non-stationary. Second, most existing methods optimize a single objective, typically predictive power, while ignoring other important properties of a high-quality alpha pool. Motivated by these challenges, we propose AlphaPareto, an RL method for formulaic alpha discovery. To address non-stationarity, AlphaPareto augments the state to include both the alpha under construction and the current alpha pool, and applies a large language model (LLM) to encode the pool. This design allows the agent to adapt to the evolving search environment. To overcome the limitation of single-objective reward design, AlphaPareto replaces the scalar reward with a multi-objective vector-valued reward that simultaneously captures predictive power, temporal stability, perturbation robustness, and diversity, and optimizes these objectives through a Pareto-regularized learning procedure. Empirical applications to real-world datasets show that our AlphaPareto method outperforms its competitors.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Zhao, Y., Yang, Z., & Zhu, Z. (2026). AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning. https://omanscience.com/en/articles/alphapareto-formulaic-alpha-discovery-with-llm-guided-multi-objective-reinforcement-learning
MLA 9
Zhao, Yingbo, et al. "AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning." https://omanscience.com/en/articles/alphapareto-formulaic-alpha-discovery-with-llm-guided-multi-objective-reinforcement-learning.
Chicago (author–date)
Zhao, Yingbo, Zeyu Yang, and Zhoufan Zhu. 2026. "AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning." https://omanscience.com/en/articles/alphapareto-formulaic-alpha-discovery-with-llm-guided-multi-objective-reinforcement-learning.
Harvard
Zhao, Y., Yang, Z. and Zhu, Z. (2026) 'AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning', Available at: https://omanscience.com/en/articles/alphapareto-formulaic-alpha-discovery-with-llm-guided-multi-objective-reinforcement-learning.
Vancouver
Zhao Y, Yang Z, Zhu Z. AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning. https://omanscience.com/en/articles/alphapareto-formulaic-alpha-discovery-with-llm-guided-multi-objective-reinforcement-learning
IEEE
Y. Zhao, Z. Yang, and Z. Zhu, "AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning," https://omanscience.com/en/articles/alphapareto-formulaic-alpha-discovery-with-llm-guided-multi-objective-reinforcement-learning.