To Trade or Not to Trade: An Agentic Approach to Estimating Market Risk Improves Trading Decisions

TL;DR

This paper presents an agentic system using large language models to discover stochastic models of financial data, which improves risk estimation and trading decisions by outperforming standard LLM agents in backtests and simulations.

Contribution

It introduces a novel agentic framework that combines LLMs with iterative model discovery for better market risk estimation and trading performance.

Findings

Model-informed trading strategies outperform standard LLM agents.

Sharpe ratios are improved across multiple equities.

The system effectively integrates model discovery with risk-based decision making.

Abstract

Large language models (LLMs) are increasingly deployed in agentic frameworks, in which prompts trigger complex tool-based analysis in pursuit of a goal. While these frameworks have shown promise across multiple domains including in finance, they typically lack a principled model-building step, relying instead on sentiment- or trend-based analysis. We address this gap by developing an agentic system that uses LLMs to iteratively discover stochastic differential equations for financial time series. These models generate risk metrics which inform daily trading decisions. We evaluate our system in both traditional backtests and using a market simulator, which introduces synthetic but causally plausible price paths and news events. We find that model-informed trading strategies outperform standard LLM-based agents, improving Sharpe ratios across multiple equities. Our results show that combining LLMs with agentic model discovery enhances market risk estimation and enables more profitable trading decisions.