GIFT uses LLMs for factor-guided state enhancement, risk-rule reward shaping, and diagnostic refinement in PPO financial RL, then fixes the interface to improve out-of-sample risk-adjusted performance.
Mathematical Finance , volume =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MetaRL pre-trained on GBWM problems delivers near-optimal dynamic strategies in 0.01s achieving 97.8% of DP optimal utility and handles larger problems where DP fails.
citing papers explorer
-
GIFT: LLM-Guided State-Reward Interface for Financial Reinforcement Learning
GIFT uses LLMs for factor-guided state enhancement, risk-rule reward shaping, and diagnostic refinement in PPO financial RL, then fixes the interface to improve out-of-sample risk-adjusted performance.
-
A Meta Reinforcement Learning Approach to Goals-Based Wealth Management
MetaRL pre-trained on GBWM problems delivers near-optimal dynamic strategies in 0.01s achieving 97.8% of DP optimal utility and handles larger problems where DP fails.