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

arXiv: https://arxiv.org/abs/2503.05346 · HTML: https://mlsanity.com/paper/2503.05346/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 71 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [AutoDroid: LLM-powered Task Automation in Android](https://mlsanity.com/paper/2308.15272/) (2023)
- [Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models](https://mlsanity.com/paper/2102.02503/) (2021)
- [LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters](https://mlsanity.com/paper/2308.08469/) (2023)
- [Large Language Models are Few-Shot Health Learners](https://mlsanity.com/paper/2305.15525/) (2023)
- [Penetrative AI: Making LLMs Comprehend the Physical World](https://mlsanity.com/paper/2310.09605/) (2023)
- [CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules](https://mlsanity.com/paper/2310.08992/) (2023)
- [Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation](https://mlsanity.com/paper/2312.03003/) (2023)
- [HARGPT: Are LLMs Zero-Shot Human Activity Recognizers?](https://mlsanity.com/paper/2403.02727/) (2024)
- [LLMSense: Harnessing LLMs for High-level Reasoning Over Spatiotemporal Sensor Traces](https://mlsanity.com/paper/2403.19857/) (2024)
- [Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI](https://mlsanity.com/paper/2312.14229/) (2023)
- [Prompt Chaining or Stepwise Prompt? Refinement in Text Summarization](https://mlsanity.com/paper/2406.00507/) (2024)
- [A Queueing Theoretic Perspective on Low-Latency LLM Inference with Variable Token Length](https://mlsanity.com/paper/2407.05347/) (2024)
- [ADMarker: A Multi-Modal Federated Learning System for Monitoring Digital Biomarkers of Alzheimer's Disease](https://mlsanity.com/paper/2310.15301/) (2023)
- [GPIoT: Tailoring Small Language Models for IoT Program Synthesis and Development](https://mlsanity.com/paper/2503.00686/) (2025)
- [FedConv: A Learning-on-Model Paradigm for Heterogeneous Federated Clients](https://mlsanity.com/paper/2502.20639/) (2025)
- [Forgetful Large Language Models: Lessons Learned from Using LLMs in Robot Programming](https://mlsanity.com/paper/2310.06646/) (2023)
- [SensorBench: Benchmarking LLMs in Coding-Based Sensor Processing](https://mlsanity.com/paper/2410.10741/) (2024)

## Built on by (most cited first, 17 of 17)

- [ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions](https://mlsanity.com/paper/2505.14668/) (2025)
- [AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management](https://mlsanity.com/paper/2512.10371/) (2025)
- [ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild](https://mlsanity.com/paper/2512.06721/) (2025)
- [Skilled AI Agents for Embedded and IoT Systems Development](https://mlsanity.com/paper/2603.19583/) (2026)
- [From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications](https://mlsanity.com/paper/2505.22311/) (2025)
- [Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices](https://mlsanity.com/paper/2512.06443/) (2025)
- [Towards Privacy-Preserving and Personalized Smart Homes via Tailored Small Language Models](https://mlsanity.com/paper/2507.08878/) (2025)
- [AutORAN: LLM-driven Natural Language Programming for Agile xApp Development](https://mlsanity.com/paper/2603.18604/) (2026)
- [iPanda: An LLM-based Agent for Automated Conformance Testing of Communication Protocols](https://mlsanity.com/paper/2507.00378/) (2025)
- [AutoBridge: Automating Smart Device Integration with Centralized Platform](https://mlsanity.com/paper/2507.23178/) (2025)
- [DeepFeature: LLM-Empowered Context-aware Feature Generation for Wearable Biosignals](https://mlsanity.com/paper/2512.08379/) (2025)
- [The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers](https://mlsanity.com/paper/2601.02045/) (2026)
- [PowerLens: Taming LLM Agents for Safe and Personalized Mobile Power Management](https://mlsanity.com/paper/2603.19584/) (2026)
- [RadioMaster: Multi-Agent System for Autonomous Radio Signal Generation](https://mlsanity.com/paper/2606.01862/) (2026)
- [CSI-Agent: LLM-Assisted Few-Shot Adaptation for Cross-Domain Wi-Fi CSI Sensing](https://mlsanity.com/paper/2609.31990/) (2026)
- [SenseAgent: An LLM Agent for Adaptive Cross-Domain IMU Sensing](https://mlsanity.com/paper/2609.32000/) (2026)
- [EdgeCraft: Automated Model Crafting for Edge IoT](https://mlsanity.com/paper/2609.35167/) (2026)

## Abstract (arXiv)

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.