AlphaQuanter: An End-to-End Tool-Augmented Agentic Reinforcement Learning Framework for Stock Trading

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Deng, Zheye, Yan, Weixiang, Yu, Changlong, Wang, Jiashu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908977092100096
author Deng, Zheye
Yan, Weixiang
Yu, Changlong
Wang, Jiashu
author_facet Deng, Zheye
Yan, Weixiang
Yu, Changlong
Wang, Jiashu
contents While Large Language Model (LLM) agents show promise in automated trading, they still face critical limitations. Prominent multi-agent frameworks often suffer from inefficiency, produce inconsistent signals, and lack the end-to-end optimization required to learn a coherent strategy from market feedback. To address this, we introduce AlphaQuanter, a single-agent framework that uses reinforcement learning (RL) to learn a dynamic policy over a transparent, tool-augmented decision workflow, which empowers a single agent to autonomously orchestrate tools and proactively acquire information on demand, establishing a transparent reasoning process. Extensive experiments demonstrate that AlphaQuanter achieves state-of-the-art performance on key financial metrics. Moreover, its interpretable reasoning reveals sophisticated strategies, offering novel and valuable insights for human traders. Our code and data can be found at https://github.com/horizon-llm/AlphaQuanter.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14264
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AlphaQuanter: An End-to-End Tool-Augmented Agentic Reinforcement Learning Framework for Stock Trading
Deng, Zheye
Yan, Weixiang
Yu, Changlong
Wang, Jiashu
Computational Engineering, Finance, and Science
While Large Language Model (LLM) agents show promise in automated trading, they still face critical limitations. Prominent multi-agent frameworks often suffer from inefficiency, produce inconsistent signals, and lack the end-to-end optimization required to learn a coherent strategy from market feedback. To address this, we introduce AlphaQuanter, a single-agent framework that uses reinforcement learning (RL) to learn a dynamic policy over a transparent, tool-augmented decision workflow, which empowers a single agent to autonomously orchestrate tools and proactively acquire information on demand, establishing a transparent reasoning process. Extensive experiments demonstrate that AlphaQuanter achieves state-of-the-art performance on key financial metrics. Moreover, its interpretable reasoning reveals sophisticated strategies, offering novel and valuable insights for human traders. Our code and data can be found at https://github.com/horizon-llm/AlphaQuanter.
title AlphaQuanter: An End-to-End Tool-Augmented Agentic Reinforcement Learning Framework for Stock Trading
topic Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2510.14264