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 LLM with an interference-aware attention bias. The proposed bias tuning mechanism injects the physical channel gain matrix directly into the self-attention scores, 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 that 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：本文研究无线网络中的功率控制问题，通过将预训练的大语言模型（LLMs）重新用作关系推理主干网络。在超连接干扰环境中，传统优化方法面临高计算成本，而标准消息传递神经网络则存在聚合瓶颈，可能掩盖关键的高干扰结构。为此，我们提出PC-LLM——一种物理信息融合框架，该框架通过干扰感知注意力偏置增强预训练LLM。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得分中，使无线拓扑结构与预训练关系先验实现显式融合，无需从头重新训练主干网络。大量实验表明，PC-LLM在持续优于传统优化方法和最先进图神经网络基线的同时，展现出对未知环境的卓越零样本泛化能力。我们进一步观察到，与拓扑相关的关系推理集中在浅层，而深层编码了任务无关的语义噪声。基于此发现，我们开发了一种轻量级适配策略，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推理代价。