# When Valid Signals Fail: Regime Boundaries Between LLM Features and RL Trading Policies

arXiv: https://arxiv.org/abs/2604.10996 · HTML: https://mlsanity.com/paper/2604.10996/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 12 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 3 of 3)

- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Recent Advances in Reinforcement Learning in Finance](https://mlsanity.com/paper/2112.04553/) (2021)
- [FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance](https://mlsanity.com/paper/2011.09607/) (2020)

## Built on by (most cited first, 1 of 1)

- [Agentic Trading: When LLM Agents Meet Financial Markets](https://mlsanity.com/paper/2605.19337/) (2026)

## Abstract (arXiv)

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 returns - rather than NLP losses. 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, LLM-derived 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.