Year: 2026
Type: conference-paper
Abstract: Can large language models (LLMs) generate continuous numerical features that improve reinforcement learning (RL) trading agents?We build a modular pipeline where a frozen LLM serves as a stateless feature extractor, transforming unstructured daily news and filings into a fixed-dimensional vector consumed by a downstream PPO agent.We introduce an automated prompt-optimization loop that treats the extraction prompt as a discrete hyperparameter and tunes it directly against the Information Coefficient-the Spearman rank correlation between predicted and realized returnsrather than text-classification objectives.The optimized prompt discovers genuinely predictive features (IC above 0.15 on held-out data).However, these valid intermediate representations do not automatically translate into downstream task performance: during a distribution shift caused by a macroeconomic shock, LLMderived features add noise, and the augmented agent under-performs a price-only baseline.In a calmer test regime the agent recovers, yet macroeconomic state variables remain the most robust driver of policy improvement.Our findings highlight a gap between feature-level validity and policy-level robustness that parallels known challenges in transfer learning under distribution shift.
Author: Zhengzhe Yang
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W7166819841