Consensus-Gated Execution: A Multi-Agent LLM Architecture for Autonomous Cryptocurrency Trading
TL;DR
Results demonstrate that adversarial debate combined with consensus-based execution gating provides a principled framework for capital preservation across diverse market regimes.
Abstract
Existing autonomous trading systems rely on collaborative or single-agent analysis, lacking structured mechanisms for adversarial deliberation across opposing market perspectives. We propose Consensus-Gated Execution (CGX), a multi-agent architecture where specialized Bull and Bear agents engage in a three-round structured debate, with a Meta-Evaluator synthesizing their arguments to gate trade execution based on consensus strength. The system is evaluated through two complementary experiments: a 52-week aggregation study (2024) and a four-year multi-regime validation (2022–2025) across 417 biweekly sessions spanning bear, recovery, bull, and mixed market conditions. Trade signals are filtered using a tunable consensus threshold, allowing the system to balance trading frequency against signal quality. In the aggregation study, CGX achieves a Sharpe ratio of 1.90 with a maximum drawdown of 11.6%, representing a 3× improvement over trend following. In the multi-year evaluation, CGX reduces maximum drawdown by 85% and annualized volatility by 86%, with the Bear gate blocking 93% of sessions during the 2022 crash versus only 12% during the 2024 bull run. These results demonstrate that adversarial debate combined with consensus-based execution gating provides a principled framework for capital preservation across diverse market regimes.