FLAG-TRADER: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading
Guojun Xiong, Zhiyang Deng, Keyi Wang, Yupeng Cao, Haohang Li, Yangyang Yu, Xueqing Peng, Mingquan Lin
Abstract
Large language models (LLMs) fine-tuned on multimodal financial data have demonstrated impressive reasoning capabilities in various financial tasks. However, they often struggle with multi-step, goal-oriented scenarios in interactive financial markets, such as trading, where complex agentic approaches are required to improve decision-making. To address this, we propose FLAG-Trader, a unified architecture integrating linguistic processing (via LLMs) with gradient-driven reinforcement learning (RL) policy optimization, in which a partially fine-tuned LLM acts as the policy network, leveraging pre-trained knowledge while adapting to the financial domain through parameter-efficient fine-tuning. Through policy gradient optimization driven by trading rewards, our framework not only enhances LLM performance in trading but also improves results on other financial-domain tasks. We present extensive empirical evidence to validate these enhancements.
BibTeX
@inproceedings{xiong-etal-2025-flag,
title = "{FLAG}-{TRADER}: Fusion {LLM}-Agent with Gradient-based Reinforcement Learning for Financial Trading",
author = "Xiong, Guojun and
Deng, Zhiyang and
Wang, Keyi and
Cao, Yupeng and
Li, Haohang and
Yu, Yangyang and
Peng, Xueqing and
Lin, Mingquan and
Smith, Kaleb E and
Liu, Xiao-Yang and
Huang, Jimin and
Ananiadou, Sophia and
Xie, Qianqian",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.716/",
doi = "10.18653/v1/2025.findings-acl.716",
pages = "13921--13934",
ISBN = "979-8-89176-256-5"
}