Cover Image

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yi, Lirong, Gay, Gregory, Leitner, Philipp
Format:	Preprint
Published:	2025
Subjects:	Software Engineering Artificial Intelligence Performance
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the Compression of Language Models for Code: An Empirical Study on CodeBERT
by: d'Aloisio, Giordano, et al.
Published: (2024)

PerfBench: Can Agents Resolve Real-World Performance Bugs?
by: Garg, Spandan, et al.
Published: (2025)

SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?
by: Ma, Jeffrey Jian, et al.
Published: (2025)

Predicting Software Performance with Divide-and-Learn
by: Gong, Jingzhi, et al.
Published: (2023)

Prompting for Performance: Exploring LLMs for Configuring Software
by: Spieker, Helge, et al.
Published: (2025)

Should AI Optimize Your Code? A Comparative Study of Classical Optimizing Compilers Versus Current Large Language Models
by: Rosas, Miguel Romero, et al.
Published: (2024)

An Empirical Study on the Performance and Energy Usage of Compiled Python Code
by: Stoico, Vincenzo, et al.
Published: (2025)

Performance of Genetic Algorithms in the Context of Software Model Refactoring
by: Cortellessa, Vittorio, et al.
Published: (2023)

An Empirical Study on Method-Level Performance Evolution in Open-Source Java Projects
by: Shahedi, Kaveh, et al.
Published: (2025)

An Empirical Study on How Architectural Topology Affects Microservice Performance and Energy Usage
by: Ristova, Irena, et al.
Published: (2026)

Energy-Efficient Software Development: A Multi-dimensional Empirical Analysis of Stack Overflow
by: Jin, Bihui, et al.
Published: (2024)

Can We Make Code Green? Understanding Trade-Offs in LLMs vs. Human Code Optimizations
by: Rani, Pooja, et al.
Published: (2025)

Learning Performance-Improving Code Edits
by: Shypula, Alexander, et al.
Published: (2023)

Rethinking Autonomy: Preventing Failures in AI-Driven Software Engineering
by: Navneet, Satyam Kumar, et al.
Published: (2025)

Employing Software Diversity in Cloud Microservices to Engineer Reliable and Performant Systems
by: Akhtarian, Nazanin, et al.
Published: (2024)

An Empirical Study of Proactive Coding Assistants in Real-World Software Development
by: Li, Lehui, et al.
Published: (2026)

Interpreting Performance Profiles with Deep Learning
by: Liu, Zhuoran
Published: (2025)

What Is the Cost of Energy Monitoring? An Empirical Study on the Overhead of RAPL-Based Tools
by: Diamond, Jeremy, et al.
Published: (2026)

LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systems
by: Wu, Siyu, et al.
Published: (2026)

On the Role of Search Budgets in Model-Based Software Refactoring Optimization
by: Diaz-Pace, J. Andres, et al.
Published: (2023)

SysLLMatic: Large Language Models are Software System Optimizers
by: Peng, Huiyun, et al.
Published: (2025)

VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations
by: Zheng, Zhongchun, et al.
Published: (2025)

Optimas: An Intelligent Analytics-Informed Generative AI Framework for Performance Optimization
by: Zaeed, Mohammad, et al.
Published: (2026)

Investigating Execution-Aware Language Models for Code Optimization
by: Di Menna, Federico, et al.
Published: (2025)

Scalable Software as a Service Architecture
by: Dedase, Ardy
Published: (2024)

AI-driven Java Performance Testing: Balancing Result Quality with Testing Time
by: Traini, Luca, et al.
Published: (2024)

Impact of Extensions on Browser Performance: An Empirical Study on Google Chrome
by: Jin, Bihui, et al.
Published: (2024)

Formal Analysis of Metastable Failures in Software Systems
by: Alvaro, Peter, et al.
Published: (2025)

Efficiently Ranking Software Variants with Minimal Benchmarks
by: Matricon, Théo, et al.
Published: (2025)

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

Towards Assessing Spread in Sets of Software Architecture Designs
by: Cortellessa, Vittorio, et al.
Published: (2024)

Tracing Optimization for Performance Modeling and Regression Detection
by: Shahedi, Kaveh, et al.
Published: (2024)

Enabling Performant and Flexible Model-Internal Observability for LLM Inference
by: Yu, Nengneng, et al.
Published: (2026)

LLM-Vectorizer: LLM-based Verified Loop Vectorizer
by: Taneja, Jubi, et al.
Published: (2024)

A Model-driven Approach for Continuous Performance Engineering in Microservice-based Systems
by: Cortellessa, Vittorio, et al.
Published: (2023)

Leveraging AI for Productive and Trustworthy HPC Software: Challenges and Research Directions
by: Teranishi, Keita, et al.
Published: (2025)

Risk-Aware Batch Testing for Performance Regression Detection
by: Sayedsalehi, Ali, et al.
Published: (2026)

LLM Interactive Optimization of Open Source Python Libraries -- Case Studies and Generalization
by: Florath, Andreas
Published: (2023)

Root Cause Localization for Microservice Systems in Cloud-edge Collaborative Environments
by: Zhu, Yuhan, et al.
Published: (2024)

This Is Taking Too Long -- Investigating Time as a Proxy for Energy Consumption of LLMs
by: Krupp, Lars, et al.
Published: (2026)