Strat-LLM: Stratified Strategy Alignment for LLM-based Stock Trading with Real-time Multi-Source Signals

TL;DR

Strat-LLM introduces a stratified framework for aligning large language models with trading strategies, leveraging real-time multi-source signals to improve decision-making and risk management in stock trading.

Contribution

It presents a novel stratified strategy alignment framework for LLMs, tested in live trading environments with heterogeneous data sources to enhance trading utility and risk control.

Findings

Reasoning-heavy models perform best in Free Mode with internal logic.

Alignment utility varies with market regime and mode.

Mid-scale models excel under strict constraints, large models face an alignment tax.

Abstract

Large Language Models (LLMs) are evolving into autonomous trading agents, yet existing benchmarks often overlook the interplay between architectural reasoning and strategy consistency. We propose Strat-LLM, a framework grounded in Stratified Strategy Alignment. Operating in a live-forward setting throughout 2025, it integrates heterogeneous data including sequential prices, real-time news, and annual reports to eliminate look-ahead bias. Extensive stress tests on A-share and U.S. markets reveal: (1) reasoning-heavy models achieve peak utility in Free Mode via internal logic, whereas standard models require Strict Mode as a vital risk anchor; (2) alignment utility is regime-dependent, with Free and Guided modes capturing momentum in uptrending markets, while Strict Mode mitigates drawdowns in downtrends; (3) mid-scale models (35B) show optimal fidelity under strict constraints, whereas ultra-large models (122B) suffer an alignment tax under rigid rules but gain a performance premium in Guided Mode; (4) standard LLMs often fall into a high win-rate trap, optimizing for small gains at the expense of total returns, which can only be mitigated through deep reasoning or strict external guardrails. Project details are available at https://Strat-LLM.github.io.