Imagen de Portada

AI-Powered, But Power-Hungry? Energy Efficiency of LLM-Generated Code

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Solovyeva, Lola, Weidmann, Sophie, Castor, Fernando
Formato:	Preprint
Publicado:	2025
Materias:	Software Engineering
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards Green AI: Decoding the Energy of LLM Inference in Software Development
por: Solovyeva, Lola, et al.
Publicado: (2026)

Babbling Suppression: Making LLMs Greener One Token at a Time
por: Solovyeva, Lola, et al.
Publicado: (2026)

An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code
por: Weidmann, Sophie, et al.
Publicado: (2026)

Estimating the Energy Footprint of Software Systems: a Primer
por: Castor, Fernando
Publicado: (2024)

Leveraging LLMs for Automated Translation of Legacy Code: A Case Study on PL/SQL to Java Transformation
por: Solovyeva, Lola, et al.
Publicado: (2025)

Green AI: A Preliminary Empirical Study on Energy Consumption in DL Models Across Different Runtime Infrastructures
por: Alizadeh, Negar, et al.
Publicado: (2024)

Understanding Code Understandability Improvements in Code Reviews
por: Oliveira, Delano, et al.
Publicado: (2024)

AILINKPREVIEWER: Enhancing Code Reviews with LLM-Powered Link Previews
por: Trakoolgerntong, Panya, et al.
Publicado: (2025)

Language Models in Software Development Tasks: An Experimental Analysis of Energy and Accuracy
por: Alizadeh, Negar, et al.
Publicado: (2024)

The Impact of Generative AI-Powered Code Generation Tools on Software Engineer Hiring: Recruiters' Experiences, Perceptions, and Strategies
por: Chen, Alyssia, et al.
Publicado: (2024)

Evaluating Efficiency and Novelty of LLM-Generated Code for Graph Analysis
por: Nia, Atieh Barati, et al.
Publicado: (2025)

COBOLAssist: Analyzing and Fixing Compilation Errors for LLM-Powered COBOL Code Generation
por: Dau, Anh T. V., et al.
Publicado: (2026)

Computer Science Achievement and Writing Skills Predict Vibe Coding Proficiency
por: Thorgeirsson, Sverrir, et al.
Publicado: (2026)

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

LLM-based Generation of Semantically Diverse and Realistic Domain Model Instances
por: Coman, Andrei, et al.
Publicado: (2026)

CodeR3: A GenAI-Powered Workflow Repair and Revival Ecosystem
por: Zaman, Asif, et al.
Publicado: (2025)

LLM-Powered Quantum Code Transpilation
por: Siavash, Nazanin, et al.
Publicado: (2025)

Beyond Code Similarity: Benchmarking the Plausibility, Efficiency, and Complexity of LLM-Generated Smart Contracts
por: Salzano, Francesco, et al.
Publicado: (2025)

COFFE: A Code Efficiency Benchmark for Code Generation
por: Peng, Yun, et al.
Publicado: (2025)

SmartNote: An LLM-Powered, Personalised Release Note Generator That Just Works
por: Daneshyan, Farbod, et al.
Publicado: (2025)

LLM-Powered Code Vulnerability Repair with Reinforcement Learning and Semantic Reward
por: Islam, Nafis Tanveer, et al.
Publicado: (2024)

A Controlled Experiment on the Energy Efficiency of the Source Code Generated by Code Llama
por: Cursaru, Vlad-Andrei, et al.
Publicado: (2024)

TRACE: Evaluating Execution Efficiency of LLM-Based Code Translation
por: Gong, Zhihao, et al.
Publicado: (2025)

TRACE: Evaluating Execution Efficiency of LLM-Based Code Translation
por: Gong, Zhihao, et al.
Publicado: (2026)

On Evaluating the Efficiency of Source Code Generated by LLMs
por: Niu, Changan, et al.
Publicado: (2024)

Context-Aware CodeLLM Eviction for AI-assisted Coding
por: Thangarajah, Kishanthan, et al.
Publicado: (2025)

SlsReuse: LLM-Powered Serverless Function Reuse
por: Wen, Jinfeng, et al.
Publicado: (2025)

Beyond Rules: LLM-Powered Linting for Quantum Programs
por: Cassieri, Pietro, et al.
Publicado: (2026)

Correctness isnt Efficiency: Runtime Memory Divergence in LLM-Generated Code
por: Rajput, Prateek, et al.
Publicado: (2026)

Breaking Android with AI: A Deep Dive into LLM-Powered Exploitation
por: Perera, Wanni Vidulige Ishan, et al.
Publicado: (2025)

Inducing Vulnerable Code Generation in LLM Coding Assistants
por: Zeng, Binqi, et al.
Publicado: (2025)

CodeFuse-CommitEval: Towards Benchmarking LLM's Power on Commit Message and Code Change Inconsistency Detection
por: Zhang, Qingyu, et al.
Publicado: (2025)

Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation
por: Chen, Jingchang, et al.
Publicado: (2024)

Beyond Code Generation: Assessing Code LLM Maturity with Postconditions
por: He, Fusen, et al.
Publicado: (2024)

RocketPPA: Code-Level Power, Performance, and Area Prediction via LLM and Mixture of Experts
por: Abdollahi, Armin, et al.
Publicado: (2025)

Towards LLM-Powered Task-Aware Retrieval of Scientific Workflows for Galaxy
por: Cynthia, Shamse Tasnim, et al.
Publicado: (2025)

Knowledge Boundary Probing and Demand-Guided Intervention for LLM-Based Power System Code Generation
por: Wu, Hui, et al.
Publicado: (2026)

LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs
por: Liu, Kaibo, et al.
Publicado: (2024)

CodeArena: A Collective Evaluation Platform for LLM Code Generation
por: Du, Mingzhe, et al.
Publicado: (2025)

Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation
por: Yan, Hao, et al.
Publicado: (2025)