mlsanityData to 7 Oct 2026

Fin-Analyst at FinMMEval 2026 Task 3: A Live Hybrid Trading Agent with LLM Specialists and Rule-Based Signals

arXiv 2607.12233 ↗First posted 14 Jul 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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 the 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 31 references that are in the map. First posted on arXiv 14 Jul 2026.

Builds on

10 of 31 references.

References · 10

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  5. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  6. 2023Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Modelscited by 125
  7. 2024FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Makingcited by 112
  8. 2024Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Modelscited by 35
  9. 2025Can LLM-based Financial Investing Strategies Outperform the Market in Long Run?cited by 19
  10. 2025Are Generative AI Agents Effective Personalized Financial Advisors?cited by 18

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?
  2. 2024INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent
  3. 2025FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain Tools
  4. 2026FinTradeBench: A Financial Reasoning Benchmark for LLMs
  5. 2025LiveTradeBench: Seeking Real-World Alpha with Large Language Models
  6. 2025When Agents Trade: Live Multi-Market Trading Benchmark for LLM Agents
  7. 2024Large Language Model Agent in Financial Trading: A Survey
  8. 2024FinVision: A Multi-Agent Framework for Stock Market Prediction