发表机构
University of North Texas（北德克萨斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对金融市场评估任务3，提出结合LLM专家和规则信号的混合交易代理Fin-Analyst，用于特斯拉和比特币交易。通过多源信息聚合及规则投票，在特斯拉交易上取得高回报率，比特币交易表现良好，还分析了排名逆转原因及信号影响等，为后续模型改进提供依据。
AI 中文摘要
大型语言模型（LLM）交易代理在股票市场展现出有前景的表现，但仍局限于美国股票且缺乏实时部署的证据。我们提出了金融分析师（Fin-Analyst），这是一个用于2026年金融市场评估任务3的混合代理。它由一个针对特斯拉（TSLA）的元代理聚合八个专家的LLM管道，涵盖新闻、美国证券交易委员会文件、基本面、分析师预测、技术指标和社会情绪，以及针对比特币（BTC）的基于轻量级规则的三信号投票。在最终官方排行榜上，Fin-Analyst在特斯拉上以13.51%的回报率排名第一，比买入并持有策略高出28.33个百分点（夏普比率4.10，胜率88%），比特币投票持平但高于大幅下跌的基线。资产排名相对于中期表现发生了逆转，表明短期实时窗口产生对波动性敏感的排名。消融分析确定事件驱动的8-K披露是对特斯拉最有影响力的信号。错误分析表明无记忆代理会连续数天重复错误调用，基于固定阈值的比特币规则在横盘市场中因交易噪音而亏损，而LLM管道在类似条件下盈利，这促使为两种资产开发基于LLM且有记忆意识的后续模型。
英文摘要
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.
Comments14 pages, 7 tables, 1 figure. CLEF 2026 FinMMEval Task 3 Working Notes
