Reproduce “Inside the Trading Loop: Markets, Models, and Moves with LLM Agents” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Renee Jia, Di Mu, Yao Yu, Tianrui Liu

The authors describe a portfolio system where language-model analysts provide structured assessments, while fixed software rules set stock weights, cash, and orders. One paper account gained 34.5% from March 11 to August 28, 2026, versus 14.4% for SPY, but maximum drawdown was 26.8%, versus 6.3%. Deterministic fallbacks ran it throughout, so this is not an LLM-driven result.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.