多智能体LLM选股系统在真实市场中验证了其超额收益能力。
Signal or Noise in Multi-Agent LLM-based Stock Recommendations?
- 四类专业智能体协同生成股票观点，合成后形成月度推荐。
- S&P 500上月均超额收益2.18%，显著优于基准和随机选股。
- 智能体策略随市场周期动态切换，揭示出可解释的阿尔法来源。
我们首次对已部署的多智能体大模型股票推荐系统MarketSenseAI进行组合层面验证。所有信号在每个观测日实时生成，避免前瞻偏差。系统通过新闻、基本面、市场动态和宏观四类专业智能体，经合成智能体输出每月个股投资观点与推荐。研究两个问题：买入建议是否超越被动基准与随机选择？内部智能体结构如何揭示优势来源？在S&P 500样本（19个月）中，强买等权组合月均收益+2.18%，高于被动基准+1.15%（近似RSP），累计超额收益达+25.2%，在10,000次蒙特卡洛模拟中排名99.7百分位（p=0.003）。S&P 100样本（35个月）超额收益+30.5%，方向一致但因平均每月仅选约10只股票，未达统计显著性。非负最小二乘投影显示，观点嵌入与智能体嵌入存在自适应融合机制。智能体贡献随市场阶段轮动（S&P 500以基本面为主，S&P 100以宏观为主，动态模块充当偶发动量信号），且与强买持仓行业构成及可识别宏观事件同步，三重独立证据指向同一适应性机制。在S&P 500上，跨截面信息系数显著（ICIR=+0.489，p=0.024）。结果表明，多智能体LLM系统能捕捉经典因子模型之外的阿尔法，其买入信号可作为有效的标的筛选器，适用于任何组合构建流程。
原文摘要 · Abstract (English)
We present the first portfolio-level validation of MarketSenseAI, a deployed multi-agent LLM equity system. All signals are generated live at each observation date, eliminating look-ahead bias. The system routes four specialist agents (News, Fundamentals, Dynamics, and Macro) through a synthesis agent that issues a monthly equity thesis and recommendation for each stock in its coverage universe, and we ask two questions: do its buy recommendations add value over both passive benchmarks and random selection, and what does the internal agent structure reveal about the source of the edge? On the S&P 500 cohort (19 months) the strong-buy equal-weight portfolio earns +2.18%/month against a passive equal-weight benchmark of +1.15% (approximating RSP), a +25.2% compound excess, and ranks at the 99.7th percentile of 10,000 Monte Carlo portfolios (p=0.003). The S&P 100 cohort (35 months) delivers a +30.5% compound excess over EQWL with consistent direction but formal significance not reached, limited by the small average selection of ~10 stocks per month. Non-negative least-squares projection of thesis embeddings onto agent embeddings reveals an adaptive-integration mechanism. Agent contributions rotate with market regime (Fundamentals leads on S&P 500, Macro on S&P 100, Dynamics acts as an episodic momentum signal) and this agent rotation moves in lockstep with both the sector composition of strong-buy selections and identifiable macro-calendar events, three independent views of the same underlying adaptation. The recommendation's cross-sectional Information Coefficient is statistically significant on S&P 500 (ICIR=+0.489, p=0.024). These results suggest that multi-agent LLM equity systems can identify sources of alpha beyond what classical factor models capture, and that the buy signal functions as an effective universe-filter that can sit upstream of any portfolio-construction process.
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。