English

MultiHedge: Adaptive Coordination via Retrieval-Augmented Control

Multiagent Systems 2026-04-29 v1 Artificial Intelligence

Abstract

Decision-making under changing conditions remains a fundamental challenge in many real-world systems. Existing approaches often fail to generalize across shifting regimes and exhibit unstable behavior under uncertainty. This raises the research question: can retrieval-augmented LLM coordination improve the robustness of modular decision pipelines? We propose MultiHedge, a hybrid architecture where an LLM produces structured allocation decisions conditioned on retrieved historical precedents, and execution is grounded in canonical option strategies. In a controlled evaluation using U.S. equities, we compare MultiHedge to rule-based and learning-based baselines. The key result is that memory-augmented retrieval confers greater robustness and stability than increasing model scale alone. Our paper contributes a controlled computational study showing that memory and architectural design play a central role in robustness in modular decision systems.

Keywords

Cite

@article{arxiv.2604.24905,
  title  = {MultiHedge: Adaptive Coordination via Retrieval-Augmented Control},
  author = {Feliks Bańka and Jarosław A. Chudziak},
  journal= {arXiv preprint arXiv:2604.24905},
  year   = {2026}
}

Comments

8 pages, 2 figures. Accepted to the 26th International Conference on Computational Science (ICCS 2026), to appear in Springer LNCS proceedings

R2 v1 2026-07-01T12:37:59.765Z