FINRS: A Risk-Sensitive Trading Framework for Real Financial Markets

TL;DR

FinRS is a novel trading framework that integrates hierarchical analysis, dual decision-making, and multi-timescale rewards to improve profitability and risk management in volatile financial markets.

Contribution

This paper introduces FinRS, a comprehensive risk-sensitive trading framework that enhances existing LLM-based trading agents with integrated risk management mechanisms.

Findings

FinRS outperforms state-of-the-art methods in profitability.

FinRS demonstrates increased stability across diverse market conditions.

The framework effectively balances return objectives with downside risk constraints.

Abstract

Large language models (LLMs) have shown strong reasoning capabilities and are increasingly explored for financial trading. Existing LLM-based trading agents, however, largely focus on single-step prediction and lack integrated mechanisms for risk management, which reduces their effectiveness in volatile markets. We introduce FinRS, a risk-sensitive trading framework that combines hierarchical market analysis, dual-decision agents, and multi-timescale reward reflection to align trading actions with both return objectives and downside risk constraints. Experiments on multiple stocks and market conditions show that FinRS achieves superior profitability and stability compared to state-of-the-art methods.