Multi agent risk aware system improves cryptocurrency swing trading
SwingGuard: Risk-Conditioned Multi-Agent Swing Trading with Dual-Timescale Governance
Multiagent Systems
Summary
Cryptocurrency trading involves holding positions over time while risks can change quickly. The authors propose SwingGuard, a system that separates slower strategy formation from faster risk control, so risk influences the strategy before it is finalized and continues to govern trades frequently. This two-speed approach uses multiple agents to analyze market data and technical signals, then adjusts and audits the trades every five minutes to limit losses. Tests with Bitcoin and Ether show better risk-adjusted returns compared to approaches that consider risk only after strategy creation.
What this means in practice
- •For cryptocurrency trading teams: Use a dual-timescale system to generate and govern cryptocurrency swing trading strategies that adapt to rapid risk changes while maintaining stable exposure.
- •For financial risk engineers: Implement a high-frequency risk controller that audits and constrains portfolio execution in live trading systems to improve risk-adjusted returns.
Authors
Junzhou Su, Yichen Luo, Yebo Feng, Teng Li, Jiahua Xu
Abstract
Cryptocurrency swing trading spans mismatched timescales: positions remain active while market and event risk can change within minutes. However, many predictive and large language model (LLM)-based trading systems assess risk after strategy generation or run both functions at the same cadence, leaving proposals unconditioned by current risk and exposure weakly governed between revisions. We propose SwingGuard, a dual-timescale, long-only multi-agent framework for risk-conditioned strategy generation. At the strategy timescale, specialized analysts synthesize point-in-time technical, sentiment, on-chain, and macroeconomic evidence through bullish-bearish deliberation. The resulting evidence and current risk context are then combined by a Portfolio Architect to form a target position. At the governance timescale, a five-minute Risk Controller performs conditional diagnosis, maintains persistent risk states with staged recovery, audits the proposal, and constrains execution until the next strategy revision. This design allows risk to shape the feasible strategy before proposal finalization while continuing to govern the active position afterward. Evaluations on Bitcoin (BTC) and Ether (ETH) show that SwingGuard preserves positive returns after transaction costs while maintaining shallow drawdowns and strong risk-adjusted performance on both assets. The exposure-capped joint portfolio achieves a Sharpe ratio of 2.98, compared with 2.79 for an otherwise identical Post-hoc Risk variant. Structured traces further link risk evidence and state transitions to strategy constraints and executed position changes, providing an auditable framework for asynchronous cryptocurrency swing trading. Overall, the results indicate that conditioning strategy formation on current risk, together with persistent high-frequency governance, improves risk-adjusted performance without sacrificing auditability.