Next-generation edge intelligence is anticipated to bring huge benefits to various applications, e.g., offloading systems. However, traditional deep offloading architectures face several issues, including heterogeneous constraints, partial perception, uncertain generalization, and lack of tractability. In this context, the integration of offloading with large language models (LLMs) presents numerous advantages. Therefore, we propose an LLM-Based Offloading (LAMBO) framework for mobile edge computing (MEC), which comprises four components: (i) Input embedding (IE), which is used to represent the information of the offloading system with constraints and prompts through learnable vectors with high quality; (ii) Asymmetric encoderdecoder (AED) model, which is a decision-making module with a deep encoder and a shallow decoder. It can achieve high performance based on multi-head self-attention schemes; (iii) Actor-critic reinforcement learning (ACRL) module, which is employed to pre-train the whole AED for different optimization tasks under corresponding prompts; and (iv) Active learning from expert feedback (ALEF), which can be used to finetune the decoder part of the AED while adapting to dynamic environmental changes. Our simulation results corroborate the advantages of the proposed LAMBO framework.

翻译：下一代边缘智能有望为各类应用（例如卸载系统）带来巨大收益。然而，传统的深度卸载架构面临异构约束、部分感知、泛化不确定性及可处理性不足等问题。在此背景下，将卸载与大语言模型（LLM）相结合展现出诸多优势。为此，我们提出一种面向移动边缘计算（MEC）的基于大语言模型的卸载（LAMBO）框架，该框架包含四个组件：（i）输入嵌入（IE），用于通过高质量可学习向量，以约束和提示形式表示卸载系统信息；（ii）非对称编码器-解码器（AED）模型，该决策模块采用深度编码器与浅层解码器，基于多头自注意力机制实现高性能；（iii）演员-评论家强化学习（ACRL）模块，用于在不同优化任务及对应提示下对整体AED进行预训练；（iv）专家反馈主动学习（ALEF），可在适应动态环境变化的同时微调AED的解码器部分。仿真结果验证了所提LAMBO框架的优势。