Hybrid LLM and Rule-Based Trading Agent Tops FinMMEval 2026 Task 3 Leaderboard

Jul 15, 2026

A hybrid trading agent, Fin-Analyst, combining eight LLM specialists with rule-based signals, achieved first place on the FinMMEval 2026 Task 3 leaderboard for Tesla (TSLA), delivering a +13.51% return and a Sharpe ratio of 4.10. The agent uses LLMs to analyze diverse financial data sources, aggregated by a Meta-Agent, while a rule-based approach was used for Bitcoin. The study also found that memoryless agents tend to repeat errors and that fixed-threshold rules underperform LLM pipelines in sideways markets.

Why it matters: This work demonstrates a significant advance in the practical deployment of LLM-based trading agents, showing strong real-world performance and offering insights for future agent design.

Full story at: arXiv Computation and Language ↗