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

• URL: http://arxiv.org/abs/2607.12233v1
• Date: Tue, 14 Jul 2026 00:27:07 GMT
• Title: Fin-Analyst at FinMMEval 2026 Task 3: A Live Hybrid Trading Agent with LLM Specialists and Rule-Based Signals
• Abstract summary: Fin-Analyst is 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)<n>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)<n>Relative to the interim performance, the asset ranking reversed, indicating that short live windows yield volatility-sensitive rankings
• Score: 1.9607607228028596
• License: http://creativecommons.org/licenses/by/4.0/
• 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 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.

Related papers

• FinDeepIndicator: Benchmarking Deep Research Agents in End-to-End Financial Indicator Construction [57.909515451254855]
  FinDeepIndicator is the first benchmark dedicated to evaluating Deep Research (DR) agents in end-to-end financial indicator construction.<n>It evaluates DR agents across four stages in indicator construction: formula specification, data collection, indicator calculation, and answer generation.<n>It contains 3,350 curated question-answer pairs derived from both U.S. and Chinese markets, 10 years of historical financial data, and 800 listed companies.
  arXiv  Detail & Related papers  (2026-08-01T16:54:41Z)
• Paper Agents, Paper Gains: An Empirical Analysis of DeFi Investment Agents [1.2615560815195466]
  DeFi investment agents, systems that use AI for autonomous on-chain trading, have attained over USD 3 billion in combined token valuations since late 2024.<n>We survey over 1,900 AI-tagged crypto projects, filter to investment-focused agents, and curate 10 representative projects spanning strategy and observability dimensions.
  arXiv  Detail & Related papers  (2026-05-27T23:21:42Z)
• From Knowing to Doing: A Memory-Controlled Benchmark for LLM Trading Agents on Stock Markets [34.699961175708815]
  KTD-Fin is an end-to-end stock-market trading benchmark.<n>It separates historical market memory from investment decision-making.<n>It incorporates a Barra-style performance attribution framework.
  arXiv  Detail & Related papers  (2026-05-27T11:57:10Z)
• CN-Buzz2Portfolio: A Chinese-Market Dataset and Benchmark for LLM-Based Macro and Sector Asset Allocation from Daily Trending Financial News [21.498084305999992]
  Large Language Models (LLMs) are rapidly transitioning from static Natural Language Processing (NLP) tasks to acting as dynamic decision-making agents.<n>Direct live trading is irreproducible and prone to outcome bias by confounding luck with skill, whereas existing static benchmarks are often confined to entity-level stock picking and ignore broader market attention.<n>This work provides new insights into the alignment between general reasoning and financial decision-making, and all data, codes, and experiments are released to promote sustainable financial agent research.
  arXiv  Detail & Related papers  (2026-03-18T02:31:28Z)
• When Agents Trade: Live Multi-Market Trading Benchmark for LLM Agents [74.55061622246824]
  Agent Market Arena (AMA) is the first lifelong, real-time benchmark for evaluating Large Language Model (LLM)-based trading agents.<n>AMA integrates verified trading data, expert-checked news, and diverse agent architectures within a unified trading framework.<n>It evaluates agents across GPT-4o, GPT-4.1, Claude-3.5-haiku, Claude-sonnet-4, and Gemini-2.0-flash.
  arXiv  Detail & Related papers  (2025-10-13T17:54:09Z)
• An Adaptive Multi Agent Bitcoin Trading System [0.0]
  This paper presents a Multi Agent Bitcoin Trading system that utilizes Large Lan- guage Models (LLMs) for alpha generation and portfolio management in the cryptocur- rencies market.<n>The proposed framework overcomes this by structuring LLMs into specialised agents for technical analysis, sentiment evaluation, decision-making, and performance reflection.<n>Back-testing on Bitcoin price data from July 2024 to April 2025 shows consistent outperformance across market regimes.
  arXiv  Detail & Related papers  (2025-10-09T10:55:52Z)
• StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets? [44.10622904101254]
  Large language models (LLMs) have recently demonstrated strong capabilities as autonomous agents.<n>We introduce StockBench, a benchmark designed to evaluate LLM agents in realistic, multi-month stock trading environments.<n>Our evaluation shows that while most LLM agents struggle to outperform the simple buy-and-hold baseline, several models demonstrate the potential to deliver higher returns and manage risk more effectively.
  arXiv  Detail & Related papers  (2025-10-02T16:54:57Z)
• Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents [69.58565132975504]
  Large language models (LLMs) have demonstrated remarkable capabilities in natural language tasks.<n>We present the Agent Trading Arena, a virtual zero-sum stock market in which LLM-based agents engage in competitive multi-agent trading.
  arXiv  Detail & Related papers  (2025-02-25T08:41:01Z)
• When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments [55.19252983108372]
  We have developed a multi-agent AI system called StockAgent, driven by LLMs. The StockAgent allows users to evaluate the impact of different external factors on investor trading. It avoids the test set leakage issue present in existing trading simulation systems based on AI Agents.
  arXiv  Detail & Related papers  (2024-07-15T06:49:30Z)
• Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models [48.87381259980254]
  We document the capability of large language models (LLMs) like ChatGPT to predict stock market reactions from news headlines without direct financial training.<n>Using post-knowledge-cutoff headlines, GPT-4 captures initial market responses, achieving approximately 90% portfolio-day hit rates for the non-tradable initial reaction.
  arXiv  Detail & Related papers  (2023-04-15T19:22:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.