EMNLP Findings2025
IoTMigrator: LLM-driven Embedded IoT Code Migration across Different OSes for Cloud-device Integration
Abstract
The increasing prevalence of embedded systems has necessitated manufacturers to migrate product code, transferring existing products to new embedded operating systems (OSes) for getting better compatibility and performance. Since manufacturers' product code predominantly employs the Thing Specification Language (TSL) paradigm for cloud connectivity, migrated code consequently adheres to the same TSL standard. However, embedded code migration under the TSL paradigm proves more complex than conventional code migration. Neither outline-based code generation nor common code translation techniques can adequately address this challenge, despite their prevalence in existing systems. There exists a growing demand for a algorithm tailored to TSL paradigm embedded code migration. In response to this demand, we have developed IoTMigrator that employs a multi-agent pipeline to handle the issue. The key insight of our algorithm is the TSL enhancer, specifically designed for the characteristics of the TSL paradigm, which serves as a crucial component in the agent pipeline. To demonstrate the superiority of our algorithm, we have established our own benchmark, which includes six tasks across two OSes, RIOT and Zephyr. We adopted two key metrics: compilation pass rate and task completeness score. The experiment results show that our algorithm outperforms the baseline by an average of at least 50.5% for pass rate and 13.0% for completeness across all tasks in RIOT, and at least 83.4% for pass rate and 18.4% for completeness in Zephyr. This work will be open-sourced in the future.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Securing Retrieval-Augmented Code Generation via Contextual Knowledge Injection: A Case for Embedded IoT Applications cites AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications
- AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications cites CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
Cited by top-tier papers1
Builds on6
- CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modulesHung Le, Hailin Chen, Amrita Saha, Akash Gokul et al.ICLR 2024 · 73 citations
- Exploring and Unleashing the Power of Large Language Models in Automated Code TranslationZhen Yang, Fang Liu, Zhongxing Yu, Jacky Wai Keung et al.FSE 2024 · 72 citations
- CodeGen4Libs: A Two-Stage Approach for Library-Oriented Code GenerationMingwei Liu, Tianyong Yang, Yiling Lou, Xueying Du et al.ASE 2023 · 31 citations
- MapCoder: Multi-Agent Code Generation for Competitive Problem SolvingMd. Ashraful Islam, Mohammed Eunus Ali, Md. Rizwan ParvezACL 2024 · 29 citations
- AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT ApplicationsLeming Shen, Qiang Yang, Yuanqing Zheng, Mo LiMobiCom 2025 · 14 citations
Related papers
- EmbedAgent: Benchmarking Large Language Models in Embedded System DevelopmentRuiyang Xu, Jialun Cao, Mingyuan Wu, Wenliang Zhong et al.ICSE 2026
- TinyLink 2.0: integrating device, cloud, and client development for IoT applicationsGaoyang Guan, Borui Li, Yi Gao, Yuxuan Zhang et al.MobiCom 2020 · 17 citations
- IntentTester: Intent-Driven Multi-agent Framework for Cross-Library Test MigrationYi Gao, Ziyuan Zhang, Xing Hu, Xiaohu Yang et al.FSE 2026
- Agentic Specification Generator for Move ProgramsYu-Fu Fu, Meng Xu, Taesoo KimASE 2025 · 1 citation
- KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging HardwareJiayi Nie, Haoran Wu, Yao Lai, Zeyu Cao et al.ICML 2026 · 6 citations
