Saved in:
Bibliographic Details
Main Authors: Yang, Jing, Wu, Yichao, Liu, Jianan, Liang, Penghao, Yuan, Mengwei, Li, Xianyou, Yan, Weiran
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.25311
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918520858607616
author Yang, Jing
Wu, Yichao
Liu, Jianan
Liang, Penghao
Yuan, Mengwei
Li, Xianyou
Yan, Weiran
author_facet Yang, Jing
Wu, Yichao
Liu, Jianan
Liang, Penghao
Yuan, Mengwei
Li, Xianyou
Yan, Weiran
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25311
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Recursive Multi-Agent Trading System: Iterative Optimized Portfolio Strategy Under Geopolitical Uncertainty
Yang, Jing
Wu, Yichao
Liu, Jianan
Liang, Penghao
Yuan, Mengwei
Li, Xianyou
Yan, Weiran
Multiagent Systems
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.
title Recursive Multi-Agent Trading System: Iterative Optimized Portfolio Strategy Under Geopolitical Uncertainty
topic Multiagent Systems
url https://arxiv.org/abs/2605.25311