Trading system using language models beats S&P 500 in 2026

Inside the Trading Loop: Markets, Models, and Moves with LLM Agents

Artificial Intelligence

Summary

This paper studies a trading system that uses large language models (LLMs) to analyze company news and economic data, combined with other methods to decide which stocks to buy or sell. The system’s portfolio delivered a higher return than a popular stock market fund between March and August 2026, though it also had bigger losses at times. The authors explored how different design choices affect performance, like when to ask the LLM for advice and how to handle cash reserves. Their approach showcases how AI can assist but not fully replace traditional trading rules.

What this means in practice

  • For quantitative trading teams: Integrate LLM-generated financial insights with algorithmic trading strategies to potentially enhance portfolio returns compared to standard benchmarks.
  • For financial technology developers: Develop hybrid trading platforms combining natural language understanding of market data with rule-based execution to support investment decision-making.$Commercial implications: Enables building advanced AI-enhanced trading software targeting asset managers seeking LLM-powered market analysis and automated trade execution.

Authors

Renee Jia, Di Mu, Yao Yu, Tianrui Liu

Abstract

We built a hybrid multi-agent trading system that combines large language model (LLM) analysts with momentum-based portfolio construction and rule-based execution. Company-news and macroeconomic agents return structured reports to a coordinator that sets stock weights and cash reserves. We evaluate the portfolio engine using its broker-recorded paper account, which operated with deterministic fallbacks, and compare LLM-enabled configurations through retrospective replays. From March 11 to August 28, 2026, the account returned 34.5%, compared with 14.4% for the S&P 500 fund SPY over the same dates. This raw return advantage came with a larger maximum drawdown. Reconstructed policies also finish above matched SPY and QQQ references when assessments are used in the same session or deferred to the next. Design comparisons examine cash authority, selective invocation, and response contracts. A constant-cash control gives a return estimate close to stance-based sizing, and shorter report contracts improve observed parsing but can change recommendations.