Recursive Multi-Agent Trading System: Iterative Optimized Portfolio Strategy Under Geopolitical Uncertainty
2026-05-25 • Multiagent Systems
Multiagent Systems
AI summaryⓘ
The authors developed RMATS, a trading system made up of four expert agents that work together through a manager agent to improve decision-making. They tested RMATS over two years on 24 different assets and found it lost less money during bad market times compared to other methods. Although it didn’t always make the most profit during strong market ups, each part of the system helped reduce losses. This makes RMATS useful for investors who want to protect their money during uncertain events like geopolitical stress. The authors show it can better guard against big drops in value than some traditional approaches.
multi-agent systemsrecursive feedbackmaximum drawdownportfolio optimizationgeopolitical riskrisk managementablation studybull marketcapital preservationfinancial stress scenarios
Authors
Jing Yang, Yichao Wu, Jianan Liu, Penghao Liang, Mengwei Yuan, Xianyou Li, Weiran Yan
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.