一句话：提出 LAMDA，用 LLM 端到端生成并优化满足边缘设备精度与时延约束的 DNN。
边缘设备上部署 AI 应用是重要软件工程难题，现有剪枝与 NAS 自动化不足。本文提出 LAMDA，将自适应 AI 部署视为自动化模型生成问题：让 LLM 端到端设计、精化并优化 DNN。其关键是把复杂 DNN 计算图序列化为结构化文本，使 LLM 能理解和操纵模型架构；并引入反馈驱动优化循环，利用经训练的经验性能模型关联架构模式与设备端延迟，使 LLM 能针对非功能需求推理优化；同时用上下文管理与验证抑制架构“幻觉”。在公开基准与真实边缘设备上的实验表明，该框架可自主生成并适配满足精度与时延约束的 DNN，推进 AI 边缘设备的自动适配。
The deployment of AI-powered applications on resource-constrained edge devices presents a significant software engineering challenge. While Pruning and Neural Architecture Search (NAS) have shown promise in optimizing model efficiency, their application in edge device deployment is often limited by low levels of automation. In this paper, we introduce LLM-based Adaptive Model Generation (LAMDA), a novel framework that tackle the challenge of adaptive AI deployment as an automated model generation problem. LAMDA empowers an LLM to perform end-to-end design, refinement, and optimization of DNNs to meet the specific hardware constraints. Our approach makes two primary contributions. First, we introduce a serialization technique that transforms complex DNN computation graphs into a structured textual representation that makes model architectures comprehensible and manipulable by an LLM. Further, to ground the generation process in real-world hardware constraints, we integrate a feedback-driven optimization loop. This loop leverages an empirical performance model, trained to correlate architectural patterns with on-device latency, enabling the LLM to reason about and optimize for non-functional requirements. To mitigate architectural “hallucinations”, we incorporate context management and validation to ensure valid generation. We evaluate LAMDA through extensive experiments on public benchmarks and real-world edge devices. The results demonstrate that our framework can autonomously generate and adapt DNNs that satisfy deployment-specific accuracy and latency constraints, significantly advancing the state-of-the-art in automated software adaptation for the AI-enabled edge devices.
@inproceedings{paperbot11829,
title = {End-to-End Model Generation with Large Language Models for Adaptive IoT Application Deployment},
author = {Zhenyu Wen and Jintao Feng and Nanjie Yao and Di Wu and Cong Wang and Mincheng Wu and Jianbin Qin and Shibo He},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3787771}
}