用历史数据增强大模型决策，让系统更稳更可靠。
MultiHedge: Adaptive Coordination via Retrieval-Augmented Control
- 大模型结合检索的历史案例做分配决策
- 在美股测试中比单纯加大模型更稳定
- 适合需要高鲁棒性的自动化决策场景
在变化环境中做出决策仍是众多现实系统的核心挑战。现有方法往往难以跨状态泛化，在不确定性下表现不稳定。本研究提出多策略协同框架 MultiHedge：基于检索的历史先例，由大语言模型生成结构化分配决策，执行则锚定在标准选项策略上。在美股市值数据集上，与规则和学习基线对比，结果表明：引入记忆检索带来的鲁棒性提升，超过单纯扩大模型规模的效果。本文通过受控计算实验，验证了记忆机制与架构设计在模块化决策系统中的核心作用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。