This paper investigates the power control problem in wireless networks by repurposing pre-trained large language models (LLMs) as relational reasoning backbones. In hyper-connected interference environments, traditional optimization methods face high computational cost, while standard message passing neural networks suffer from aggregation bottlenecks that can obscure critical high-interference structures. In response, we propose PC-LLM, a physics-informed framework that augments a pre-trained Transformer with an interference-aware attention bias. The proposed bias tuning mechanism injects the physical channel gain matrix directly into the self-attention logits, enabling explicit fusion of wireless topology with pre-trained relational priors without retraining the backbone from scratch. Extensive experiments demonstrate that PC-LLM consistently outperforms both traditional optimization methods and state-of-the-art graph neural network baselines, while exhibiting exceptional zero-shot generalization to unseen environments. We further observe a structural-semantic decoupling phenomenon: Topology-relevant relational reasoning is concentrated in shallow layers, whereas deeper layers encode task-irrelevant semantic noise. Motivated by this finding, we develop a lightweight adaptation strategy that reduces model depth by 50\%, significantly lowering inference cost while preserving state-of-the-art spectral efficiency.

翻译：本文通过将预训练大语言模型（LLMs）重新用作关系推理主干，研究无线网络中的功率控制问题。在超连接干扰环境中，传统优化方法面临高昂的计算成本，而标准消息传递神经网络则受限于聚合瓶颈，可能掩盖关键的高干扰结构。为此，我们提出PC-LLM，一个融合物理信息的框架，通过干扰感知的注意力偏置增强预训练的Transformer。所提出的偏置调优机制将物理信道增益矩阵直接注入自注意力对数中，实现了无线拓扑与预训练关系先验的显式融合，而无需从头重新训练主干网络。大量实验表明，PC-LLM在性能上持续优于传统优化方法和最先进的图神经网络基线，同时对未见环境展现出卓越的零样本泛化能力。我们进一步观察到一种结构-语义解耦现象：与拓扑相关的推理主要集中在浅层，而更深层则编码了与任务无关的语义噪声。基于这一发现，我们开发了一种轻量级适应策略，将模型深度减少50%，在保持最先进频谱效率的同时，显著降低了推理成本。