Large language models (LLMs) are increasingly being explored as high-level decision modules in closed-loop systems, but their stochastic nature makes safe integration challenging. In this paper, we propose LLM-Steered Power Allocation, a dual-process architecture for parallel QPSK channels inspired by Kahneman's System 1/System 2 framework. A fast numerical optimizer (System 1) continuously performs projected gradient ascent on a weighted mutual-information objective, while an LLM navigator (System 2) periodically interprets natural-language policies and updates only the channel weights and the operational power budget. The LLM never manipulates the power-allocation variables directly, and constraint satisfaction is enforced structurally by the optimizer. To mitigate LLM unreliability, we further incorporate multi-layer guardrails including normalization, exponential moving-average smoothing, and fallback mechanisms. Numerical experiments on an 8-channel system show that, with a fixed optimization core and unchanged system prompt, different natural-language policies induce qualitatively different operating points, including throughput-oriented allocation, channel prioritization, power-aware operation, and channel shutdown. In addition, under an abrupt channel-gain reversal, the proposed system autonomously reconfigures its steering signals and reduces the final mutual-information spread by 60% compared with the optimizer alone. These results suggest that LLMs can serve as policy interpreters for safe, flexible reconfiguration of communication-system optimizers without controller reimplementation.

翻译：大型语言模型（LLM）正逐渐被探索作为闭环系统中的高层决策模块，但其随机性本质使得安全集成面临挑战。本文受卡尼曼系统1/系统2框架启发，提出了一种针对并行QPSK信道的双进程架构——LLM引导的功率分配。快速数值优化器（系统1）持续执行加权互信息目标的投影梯度上升，而LLM导航器（系统2）则周期性解读自然语言策略，仅更新信道权重和运行功率预算。LLM从不直接操控功率分配变量，约束满足由优化器从结构上保证。为缓解LLM不可靠性，我们进一步集成了包括归一化、指数移动平均平滑和回退机制在内的多层防护措施。对8信道系统的数值实验表明，在固定优化核心和不变系统提示词条件下，不同自然语言策略会诱导出性质各异的运行状态，包括吞吐量导向分配、信道优先级设置、功率感知运行及信道关闭。此外，在信道增益突变的场景下，所提系统可自主重构引导信号，与单独使用优化器相比，最终互信息分散度降低60%。这些结果表明，LLM可作为策略解释器，在不需重构控制器的情况下，实现通信系统优化器的安全灵活重构。