Abstract
This paper presents a novel hierarchical framework for portfolio optimization, integrating lightweight Large Language Models (LLMs) with Deep Reinforcement Learning (DRL) to combine sentiment signals from financial news with traditional market indicators. Our three-tier architecture employs base RL agents to process hybrid data, meta-agents to aggregate their decisions, and a super-agent to merge decisions based on market data and sentiment analysis. Evaluated on data from 2018 to 2024, after training on 2000-2017, the framework achieves a 26% annualized return and a Sharpe ratio of 1.2, outperforming equal-weighted and S&P 500 benchmarks. Key contributions include scalable cross-modal integration, a hierarchical RL structure for enhanced stability, and open-source reproducibility.
Abstract (translated)
本文提出了一种新颖的分层框架，用于投资组合优化，该框架将轻量级大型语言模型（LLMs）与深度强化学习（DRL）相结合，以融合来自金融新闻的情绪信号和传统的市场指标。我们的三层架构包括基础RL代理来处理混合数据、元代理来汇总他们的决策以及超级代理来基于市场数据和情绪分析进行合并决策。在2018年至2024年的数据上进行了评估，在2000年至2017年期间完成了训练，该框架实现了每年化收益率26%及夏普比率1.2的业绩，优于等权重基准和标普500指数。主要贡献包括可扩展的跨模态整合、增强稳定性的分层RL结构以及开源可复制性。
URL
https://arxiv.org/abs/2507.22932
