MultiHedge: LLM Coordination with Retrieval-Augmented Control

A new hybrid architecture called MultiHedge uses retrieval-augmented LLM coordination to improve decision-making under changing conditions. The system combines an LLM that produces structured allocation decisions based on historical precedents with execution grounded in canonical option strategies. In controlled evaluations using U.S. equities, MultiHedge outperformed rule-based and learning-based baselines. The key finding is that memory-augmented retrieval provides greater robustness and stability than simply increasing model scale. The research contributes a computational study showing that memory and architectural design are central to robustness in modular decision pipelines.