AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications

2025-03-07

AI Summary

To address core challenges in deploying large language models (LLMs) for AIoT applications—including privacy leakage, high query costs, opaque inference, and difficulty in result verification—this paper introduces AutoIOT: the first localized framework enabling automatic generation of formally verified, fully documented, and executable AIoT programs directly from natural language specifications. AutoIOT innovatively integrates on-device sensor data processing, iterative self-optimizing code generation, interpretable pipeline design, and automated documentation synthesis—without uploading raw sensor data. Experimental evaluation across diverse AIoT tasks demonstrates that AutoIOT-generated programs match or exceed baseline performance in accuracy and efficiency. Extensive large-scale experiments and user studies confirm AutoIOT’s high correctness, strong usability, and significant cost-effectiveness, establishing it as a practical, privacy-preserving solution for trustworthy edge intelligence.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The advent of Large Language Models (LLMs) has profoundly transformed our lives, revolutionizing interactions with AI and lowering the barrier to AI usage. While LLMs are primarily designed for natural language interaction, the extensive embedded knowledge empowers them to comprehend digital sensor data. This capability enables LLMs to engage with the physical world through IoT sensors and actuators, performing a myriad of AIoT tasks. Consequently, this evolution triggers a paradigm shift in conventional AIoT application development, democratizing its accessibility to all by facilitating the design and development of AIoT applications via natural language. However, some limitations need to be addressed to unlock the full potential of LLMs in AIoT application development. First, existing solutions often require transferring raw sensor data to LLM servers, which raises privacy concerns, incurs high query fees, and is limited by token size. Moreover, the reasoning processes of LLMs are opaque to users, making it difficult to verify the robustness and correctness of inference results. This paper introduces AutoIOT, an LLM-based automated program generator for AIoT applications. AutoIOT enables users to specify their requirements using natural language (input) and automatically synthesizes interpretable programs with documentation (output). AutoIOT automates the iterative optimization to enhance the quality of generated code with minimum user involvement. AutoIOT not only makes the execution of AIoT tasks more explainable but also mitigates privacy concerns and reduces token costs with local execution of synthesized programs. Extensive experiments and user studies demonstrate AutoIOT's remarkable capability in program synthesis for various AIoT tasks. The synthesized programs can match and even outperform some representative baselines.

Problem

• Automates AIoT application development using natural language.
• Addresses privacy and cost issues in LLM-driven AIoT solutions.
• Enhances explainability and correctness of AIoT task execution.

Innovation

• LLM-driven natural language programming for AIoT
• Local execution reduces privacy risks and costs
• Automated iterative optimization enhances code quality