用多智能体系统融合新闻与财务数据，实现透明可复现的股票预测。
MASFIN: A Multi-Agent System for Decomposed Financial Reasoning and Forecasting
- 构建多智能体框架，分工处理结构化数据与非结构化新闻。
- 八周回测中累计收益7.33%，六周跑赢三大指数基准。
- 适合关注可解释性、抗偏差金融AI的从业者与研究者。
大型语言模型（LLMs）正推动数据密集型领域变革，金融因其高风险性，对异构信号的透明、可复现分析尤为关键。传统量化方法易受幸存者偏差影响，而多数AI方案在信号整合、可复现性与计算效率上存在不足。我们提出MASFIN，一个模块化的多智能体框架，将LLMs与结构化财务指标及非结构化新闻结合，并嵌入显式偏差缓解机制。系统采用GPT-4.1-nano以保证可复现性与低成本推理，生成每周15-30只股票组成的组合，权重针对短期表现优化。八周评估中，MASFIN实现7.33%累计回报，在六周内超越标普500、纳斯达克100与道琼斯基准，尽管波动率更高。结果表明，具备偏差意识的生成式AI在金融预测中具有潜力，且模块化多智能体设计为量化金融中实用、透明、可复现的方法提供了新路径。
原文摘要 · Abstract (English)
Recent advances in large language models (LLMs) are transforming data-intensive domains, with finance representing a high-stakes environment where transparent and reproducible analysis of heterogeneous signals is essential. Traditional quantitative methods remain vulnerable to survivorship bias, while many AI-driven approaches struggle with signal integration, reproducibility, and computational efficiency. We introduce MASFIN, a modular multi-agent framework that integrates LLMs with structured financial metrics and unstructured news, while embedding explicit bias-mitigation protocols. The system leverages GPT-4.1-nano for reproducability and cost-efficient inference and generates weekly portfolios of 15-30 equities with allocation weights optimized for short-term performance. In an eight-week evaluation, MASFIN delivered a 7.33% cumulative return, outperforming the S&P 500, NASDAQ-100, and Dow Jones benchmarks in six of eight weeks, albeit with higher volatility. These findings demonstrate the promise of bias-aware, generative AI frameworks for financial forecasting and highlight opportunities for modular multi-agent design to advance practical, transparent, and reproducible approaches in quantitative finance.
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。