{"ID":2887492,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.01173","arxiv_id":"2508.01173","title":"MARS: A Meta-Adaptive Reinforcement Learning Framework for Risk-Aware Multi-Agent Portfolio Management","abstract":"Reinforcement Learning (RL) has shown significant promise in automated portfolio management; however, effectively balancing risk and return remains a central challenge, as many models fail to adapt to dynamically changing market conditions. We propose Meta-controlled Agents for a Risk-aware System (MARS), a novel framework addressing this through a multi-agent, risk-aware approach. MARS replaces monolithic models with a Heterogeneous Agent Ensemble, where each agent's unique risk profile is enforced by a Safety-Critic network to span behaviors from capital preservation to aggressive growth. A high-level Meta-Adaptive Controller (MAC) dynamically orchestrates this ensemble, shifting reliance between conservative and aggressive agents to minimize drawdown during downturns while seizing opportunities in bull markets. This two-tiered structure leverages behavioral diversity rather than explicit feature engineering to ensure a disciplined portfolio robust across market regimes. Experiments on major international indexes confirm that our framework significantly reduces maximum drawdown and volatility while maintaining competitive returns.","short_abstract":"Reinforcement Learning (RL) has shown significant promise in automated portfolio management; however, effectively balancing risk and return remains a central challenge, as many models fail to adapt to dynamically changing market conditions. We propose Meta-controlled Agents for a Risk-aware System (MARS), a novel frame...","url_abs":"https://arxiv.org/abs/2508.01173","url_pdf":"https://arxiv.org/pdf/2508.01173v2","authors":"[\"Jiayi Chen\",\"Jing Li\",\"Guiling Wang\"]","published":"2025-08-02T03:23:41Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.MA\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}