Abstract
Large language model (LLM) trading agents show promising performance in equity markets, yet remain narrowly focused on US equities with little evidence from live deployment. We present Fin-Analyst, a hybrid agent for FinMMEval 2026 Task 3: an eight-specialist LLM pipeline over news, SEC filings, fundamentals, analyst forecasts, technical indicators, and social sentiment, aggregated by a Meta-Agent for Tesla (TSLA), and a lightweight rule-based three-signal vote for Bitcoin (BTC).
On the final official leaderboard (accessed 2026-07-05), Fin-Analyst ranks first of all agents on TSLA with a +13.51% return, +28.33 points over Buy-and-Hold (Sharpe 4.10, 88% win rate), while the BTC vote ends flat yet well above a sharply falling baseline.
Relative to the interim performance, the asset ranking reversed, indicating that short live windows yield volatility-sensitive rankings. Ablation identifies event-driven 8-K disclosures as the most influential TSLA signal. Error analysis shows that memoryless agents repeat wrong calls for days at a time, and that the fixed-threshold BTC rules lost money by trading on noise in a sideways market, while the LLM pipeline gained under similar conditions, motivating a memory-aware, LLM-based successor for both assets.
Blogger's Review: The success of Fin-Analyst highlights that hybrid strategies combining LLMs and rule-based signals can significantly enhance trading performance in complex financial markets. Particularly, the memory-aware mechanism offers a new direction for future trading systems, demonstrating greater adaptability to market fluctuations compared to traditional fixed strategies.