analiza aiqbench
AlphaPareto introduces a novel reinforcement learning framework for quantitative trading that leverages LLMs to handle non-stationary alpha pools while optimizing multiple objectives like stability and diversity. By shifting from single-objective rewards to Pareto-regularized vector-valued rewards, the method addresses critical limitations in existing formulaic discovery approaches. This research advances the intersection of large language models and multi-objective optimization within high-frequency trading environments.
AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning
arXiv:2609.34188v1 Announce Type: cross 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.
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.
Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2609.34188 [stat.ML]
(or arXiv:2609.34188v1 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2609.34188 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 283 cuvinte
Subiecte conexe
AlphaRJM: Reward-Jump Memory for Stochastic Return-Guided Alpha Discovery
arXiv · 9 sept. 2026
LiveLaw Supreme Court Half-Yearly Digest: January - June 2026 [Part 2]
livelaw.in · 13 sept. 2026
How Matryoshka Sparse AutoEncoders Recover Feature Hierarchies That Vanilla SAEs Lose
LessWrong · 15 iun. 2026
Quantum-Enhanced Algorithm Cuts Shots Needed for Multi-Objective Tasks
Quantum Zeitgeist · 24 iul. 2026