混合智能交易代理在特斯拉和比特币上实现领先收益，依赖多专家LLM与规则信号协同决策。
Fin-Analyst at FinMMEval 2026 Task 3: A Live Hybrid Trading Agent with LLM Specialists and Rule-Based Signals
- 构建8个专业LLM分工处理新闻、财报等多源信息，由元代理整合决策。
- 特斯拉持仓收益+13.51%，胜过买入持有策略28.33点，夏普比4.10，胜率88%。
- 揭示事件驱动披露为关键信号，且内存感知的LLM优于固定阈值规则。
大型语言模型（LLM）交易代理在股票市场展现出良好性能，但主要集中于美国股市，且缺乏实际部署证据。本文提出Fin-Analyst，一个用于FinMMEval 2026任务3的混合型交易代理：针对特斯拉（TSLA）采用由8个专业领域LLM组成的流水线，分别处理新闻、SEC文件、基本面、分析师预测、技术指标及社交情绪，并由元代理聚合结果；针对比特币（BTC）则采用轻量级规则三信号投票机制。在2026年7月5日公布的最终官方排行榜上，Fin-Analyst在特斯拉资产上排名第一，实现+13.51%收益率，超出买入持有策略28.33点，夏普比率达4.10，胜率88%；而比特币投票结果持平，显著优于大幅下跌的基线。相较于中期表现，资产排名反转，表明短期运行窗口对波动敏感性排名影响显著。消融实验表明，事件驱动的8-K披露是特斯拉最关键的信号。错误分析发现，无记忆的代理会持续重复错误判断，而固定阈值的比特币规则在盘整市中因交易噪音亏损，相反LLM流水线在相似条件下仍能获利，这推动了面向两类资产的具备记忆能力的下一代LLM代理设计。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。