Hierarchical AI Multi-Agent Fundamental Investing: Evidence from China's A-Share Market

2025-10-24

AI Summary

This paper addresses two key challenges in fundamental investing in China’s A-share market: (1) difficulty in fusing multi-level information—macroeconomic, sectoral, and firm-specific—and (2) insufficient robustness of factor portfolios. To tackle these, we propose a hierarchical multi-agent AI framework comprising four specialized agents: a macro agent for cyclical timing, a sector agent for identifying industry rotation patterns, a firm agent performing deep financial and news-text analysis, and a portfolio agent that dynamically optimizes weights and risk budgets via reinforcement learning. The framework establishes a closed-loop decision process integrating top-down screening with bottom-up validation, enhancing scalability and noise resilience of factor combinations. Empirical evaluation on CSI 300 constituents demonstrates a 32% improvement in Sharpe ratio and a 27% reduction in maximum drawdown versus the benchmark index—outperforming both single-model baselines and state-of-the-art multi-agent trading systems. The framework delivers a reproducible, interpretable paradigm for AI-driven fundamental investing.

Technology Category

• Multiagent Systems: Other Foundations of Multi Agent Systems
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We present a multi-agent, AI-driven framework for fundamental investing that integrates macro indicators, industry-level and firm-specific information to construct optimized equity portfolios. The architecture comprises: (i) a Macro agent that dynamically screens and weights sectors based on evolving economic indicators and industry performance; (ii) four firm-level agents -- Fundamental, Technical, Report, and News -- that conduct in-depth analyses of individual firms to ensure both breadth and depth of coverage; (iii) a Portfolio agent that uses reinforcement learning to combine the agent outputs into a unified policy to generate the trading strategy; and (iv) a Risk Control agent that adjusts portfolio positions in response to market volatility. We evaluate the system on the constituents by the CSI 300 Index of China's A-share market and find that it consistently outperforms standard benchmarks and a state-of-the-art multi-agent trading system on risk-adjusted returns and drawdown control. Our core contribution is a hierarchical multi-agent design that links top-down macro screening with bottom-up fundamental analysis, offering a robust and extensible approach to factor-based portfolio construction.

Problem

• Integrating macro indicators with firm-level analysis for portfolio construction
• Developing hierarchical AI agents for fundamental investing strategies
• Optimizing equity portfolios using multi-agent reinforcement learning

Innovation

• Multi-agent AI framework integrates macro and firm data
• Reinforcement learning optimizes portfolio trading strategies
• Hierarchical design links top-down and bottom-up analysis