Cover Image

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Morabito, Roberto, Wu, Guanghan
Format:	Preprint
Published:	2025
Subjects:	Software Engineering Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Consolidating TinyML Lifecycle with Large Language Models: Reality, Illusion, or Opportunity?
by: Wu, Guanghan, et al.
Published: (2025)

Neuron-Guided Interpretation of Code LLMs: Where, Why, and How?
by: Yin, Zhe, et al.
Published: (2025)

The Machine Learning Canvas: Empirical Findings on Why Strategy Matters More Than AI Code Generation
by: Prause, Martin
Published: (2026)

Teaching Machines to Code: Smart Contract Translation with LLMs
by: Karanjai, Rabimba, et al.
Published: (2024)

NoFunEval: Funny How Code LMs Falter on Requirements Beyond Functional Correctness
by: Singhal, Manav, et al.
Published: (2024)

TransformCode: A Contrastive Learning Framework for Code Embedding via Subtree Transformation
by: Xian, Zixiang, et al.
Published: (2023)

When Fuzzing Meets LLMs: Challenges and Opportunities
by: Jiang, Yu, et al.
Published: (2024)

Automatic Identification of Machine Learning-Specific Code Smells
by: Hamfelt, Peter, et al.
Published: (2025)

Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code
by: Kim, Myeongsoo, et al.
Published: (2026)

Machine Learning Techniques for Python Source Code Vulnerability Detection
by: Farasat, Talaya, et al.
Published: (2024)

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks
by: Lu, Ruofan, et al.
Published: (2025)

SpareCodeSearch: Searching for Code Context When You Have No Spare GPU
by: Nguyen, Minh
Published: (2025)

Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages
by: Wu, Fan, et al.
Published: (2026)

An Effective Approach to Embedding Source Code by Combining Large Language and Sentence Embedding Models
by: Xian, Zixiang, et al.
Published: (2024)

Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs
by: Chen, Yujia, et al.
Published: (2026)

Migrating Code At Scale With LLMs At Google
by: Ziftci, Celal, et al.
Published: (2025)

Analysis on LLMs Performance for Code Summarization
by: Akib, Md. Ahnaf, et al.
Published: (2024)

CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval
by: Liu, Ye, et al.
Published: (2024)

aerial-autonomy-stack -- a Faster-than-real-time, Autopilot-agnostic, ROS2 Framework to Simulate and Deploy Perception-based Drones
by: Panerati, Jacopo, et al.
Published: (2026)

The Code Barrier: What LLMs Actually Understand?
by: Nikiema, Serge Lionel, et al.
Published: (2025)

Do Code LLMs Understand Design Patterns?
by: Pan, Zhenyu, et al.
Published: (2025)

Function-to-Style Guidance of LLMs for Code Translation
by: Zhang, Longhui, et al.
Published: (2025)

Evaluating the Energy-Efficiency of the Code Generated by LLMs
by: Islam, Md Arman, et al.
Published: (2025)

CodeTF: One-stop Transformer Library for State-of-the-art Code LLMs
by: Bui, Nghi D. Q., et al.
Published: (2023)

Mastering the Craft of Data Synthesis for CodeLLMs
by: Chen, Meng, et al.
Published: (2024)

Rectifier: Code Translation with Corrector via LLMs
by: Yin, Xin, et al.
Published: (2024)

A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?
by: Chen, QiHong, et al.
Published: (2024)

RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts
by: Weidener, Lukas, et al.
Published: (2026)

Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLMs
by: Xie, Chen, et al.
Published: (2025)

CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs
by: Basha, Manaal, et al.
Published: (2025)

Code for Machines, Not Just Humans: Quantifying AI-Friendliness with Code Health Metrics
by: Borg, Markus, et al.
Published: (2026)

On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation
by: Naik, Atharva
Published: (2024)

When the Specification Emerges: Benchmarking Faithfulness Loss in Long-Horizon Coding Agents
by: Yan, Lu, et al.
Published: (2026)

Can LLMs Replace Humans During Code Chunking?
by: Glasz, Christopher, et al.
Published: (2025)

Holistic Evaluation of State-of-the-Art LLMs for Code Generation
by: Zhang, Le, et al.
Published: (2025)

SpecRover: Code Intent Extraction via LLMs
by: Ruan, Haifeng, et al.
Published: (2024)

Leveraging LLMs, IDEs, and Semantic Embeddings for Automated Move Method Refactoring
by: Bellur, Abhiram, et al.
Published: (2025)

The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason
by: Liang, Shanchao, et al.
Published: (2025)

MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair
by: Dehghan, Meghdad, et al.
Published: (2024)

Coding in a Bubble? Evaluating LLMs in Resolving Context Adaptation Bugs During Code Adaptation
by: Zhang, Tanghaoran, et al.
Published: (2026)