paper-with-me

홈 › Papers

Automated Code Generation and Validation for Software Components of Microcontrollers

2025-02-26 · Sebastian Haug, Christoph Böhm, Daniel Mayer

This paper proposes a method for generating software components for embedded systems, integrating seamlessly into existing implementations without developer intervention. We demonstrate this by automatically generating hardware abstraction layer (HAL) code for GPIO operations on the STM32F407 microcontroller. Using Abstract Syntax Trees (AST) for code analysis and Retrieval-Augmented Generation (RAG) for component generation, our approach enables autonomous code completion for embedded applications.

📄 PDF Abstract BibTeX arXiv:2502.18905

Code (0)

등록된 구현이 없습니다.

Tasks

Code CompletionCode GenerationRAGRetrievalRetrieval-augmented Generation

Similar Papers 제목 키워드 기반

MarsCode Agent: AI-native Automated Bug Fixing

2024-09-02 · Yizhou Liu, Pengfei Gao, Xinchen Wang, Jie Liu 외

Recent advances in large language models (LLMs) have shown significant potential to automate various software development tasks, including code completion, test generation, and bug fixing. However, the application of LLM…

Bug fixingCode CompletionDiversityFault localization

karl. -- A Research Vehicle for Automated and Connected Driving

2026-02-09 · Jean-Pierre Busch, Lukas Ostendorf, Guido Linden, Lennart Reiher 외 arxiv

As highly automated driving is transitioning from single-vehicle closed-access testing to commercial deployments of public ride-hailing in selected areas (e.g., Waymo), automated driving and connected cooperative intelli…

Text to model via SysML: Automated generation of dynamical system computational models from unstructured natural language text via enhanced System Modeling Language diagrams

2025-07-09 · Matthew Anderson Hendricks, Alice Cicirello arxiv

This paper contributes to speeding up the design and deployment of engineering dynamical systems by proposing a strategy for exploiting domain and expert knowledge for the automated generation of a dynamical system compu…

Code Generation

SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks

2025-06-12 · Lianghong Guo, Yanlin Wang, Caihua Li, Pengyu Yang 외

Constructing large-scale datasets for the GitHub issue resolution task is crucial for both training and evaluating the software engineering capabilities of Large Language Models (LLMs). However, the traditional process f…

GitHub issue resolutionvalid

Optimizing Code Runtime Performance through Context-Aware Retrieval-Augmented Generation

2025-01-28 · Manish Acharya, Yifan Zhang, Kevin Leach, Yu Huang

Optimizing software performance through automated code refinement offers a promising avenue for enhancing execution speed and efficiency. Despite recent advancements in LLMs, a significant gap remains in their ability to…

In-Context LearningRetrievalRetrieval-augmented Generation