Language Model Guided Reinforcement Learning in Quantitative Trading
This work addresses the challenge of improving reinforcement learning adoption in quantitative trading by enhancing decision-making with language model insights, representing an incremental advancement in hybrid AI methods for finance.
The paper tackles the problem of myopic behavior and opaque policies in reinforcement learning for algorithmic trading by proposing a hybrid framework where large language models generate high-level strategies to guide RL agents. Results show that LLM guidance improves return and risk metrics, such as Sharpe Ratio and Maximum Drawdown, compared to standard RL baselines.
Algorithmic trading requires short-term tactical decisions consistent with long-term financial objectives. Reinforcement Learning (RL) has been applied to such problems, but adoption is limited by myopic behaviour and opaque policies. Large Language Models (LLMs) offer complementary strategic reasoning and multi-modal signal interpretation when guided by well-structured prompts. This paper proposes a hybrid framework in which LLMs generate high-level trading strategies to guide RL agents. We evaluate (i) the economic rationale of LLM-generated strategies through expert review, and (ii) the performance of LLM-guided agents against unguided RL baselines using Sharpe Ratio (SR) and Maximum Drawdown (MDD). Empirical results indicate that LLM guidance improves both return and risk metrics relative to standard RL.