Recursive Multi-Agent Trading System: Iterative Optimized Portfolio Strategy Under Geopolitical Uncertainty

2026-05-24

AI Summary

This study addresses multi-asset portfolio optimization under geopolitical uncertainty by proposing a recursive multi-agent trading system composed of four specialized agents—sentiment, reporting, analytics, and risk—orchestrated by a central management agent that coordinates their interactions and iterative feedback. The architecture integrates FinBERT-based sentiment analysis, mean-variance optimization (MVO), and event-driven backtesting. Evaluated over 561 trading days, the system achieves a maximum drawdown of 9.62%, significantly outperforming both standalone MVO and FinBERT sentiment benchmarks. Furthermore, in five geopolitical stress tests, it attains the lowest drawdown during event periods in three instances, demonstrating enhanced resilience to downside risk.

Abstract

Recursive Multi-Agent Trading System (RMATS) integrates four specialized agents -- Sentiment, Report, Analysis, and Risk -- coordinated through a recursive Manager Agent with iterative feedback loops. Experimental evaluation over a 561-trading-day period (January 2023 to March 2025) across a 24-asset multi-class universe demonstrates that RMATS achieves a maximum drawdown of 9.62%, lower than MVO (15.49%) and FinBERT Sentiment (15.28%), and exhibits the lowest event-period drawdown in 3 of 5 geopolitical stress scenarios tested. While RMATS underperforms return-maximizing baselines in a sustained bull market environment, ablation studies confirm the individual contribution of each agent component to downside protection. These results position RMATS as a risk-control-oriented architecture suitable for institutions prioritizing capital preservation under geopolitical uncertainty.

Problem

• geopolitical uncertainty
• portfolio strategy
• risk control
• drawdown
• capital preservation

Innovation

• Recursive Multi-Agent System
• Iterative Feedback Loop
• Geopolitical Risk
• Downside Protection
• Portfolio Optimization