paper-with-me

홈 › Papers

How Do Agents Perform Code Optimization? An Empirical Study

2025-12-25 · Huiyun Peng, Antonio Zhong, Ricardo Andrés Calvo Méndez, Kelechi G. Kalu, James C. Davis arxiv

Performance optimization is a critical yet challenging aspect of software development, often requiring a deep understanding of system behavior, algorithmic tradeoffs, and careful code modifications. Although recent advances in AI coding agents have accelerated code generation and bug fixing, little is known about how these agents perform on real-world performance optimization tasks. We present the first empirical study comparing agent- and human-authored performance optimization commits, analyzing 324 agent-generated and 83 human-authored PRs from the AIDev dataset across adoption, maintainability, optimization patterns, and validation practices. We find that AI-authored performance PRs are less likely to include explicit performance validation than human-authored PRs (45.7\% vs. 63.6\%, $p=0.007$). In addition, AI-authored PRs largely use the same optimization patterns as humans. We further discuss limitations and opportunities for advancing agentic code optimization.

📄 PDF Abstract BibTeX arXiv:2512.21757

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

VeRO: A Harness for Agents to Optimize Agents

2026-02-25 · Varun Ursekar, Apaar Shanker, Veronica Chatrath, Yuan Xue 외 arxiv

An important emerging application of coding agents is agent harness optimization: the iterative improvement of a target agent by editing and evaluating its code. Despite its relevance, the community lacks a systematic un…

Agent Factories for High Level Synthesis: How Far Can General-Purpose Coding Agents Go in Hardware Optimization?

2026-03-26 · Abhishek Bhandwaldar, Mihir Choudhury, Ruchir Puri, Akash Srivastava arxiv

We present an empirical study of how far general-purpose coding agents -- without hardware-specific training -- can optimize hardware designs from high-level algorithmic specifications. We introduce an agent factory, a t…

Empirical Asset Pricing with Large Language Model Agents

2024-09-25 · Junyan Cheng, Peter Chin

In this study, we introduce a novel asset pricing model leveraging the Large Language Model (LLM) agents, which integrates qualitative discretionary investment evaluations from LLM agents with quantitative financial econ…

Language ModelingLanguage ModellingLarge Language ModelPortfolio Optimization

An Empirical Study of Multi-Agent Collaboration for Automated Research

2026-03-31 · Yang Shen, Zhenyi Yi, Ziyi Zhao, Lijun Sun 외 arxiv

As AI agents evolve, the community is rapidly shifting from single Large Language Models (LLMs) to Multi-Agent Systems (MAS) to overcome cognitive bottlenecks in automated research. However, the optimal multi-agent coord…

Code Generation

AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agents

2025-12-26 · Bhanu Prakash Vangala, Ali Adibifar, Ashish Gehani, Tanu Malik arxiv

The rise of Large Language Models (LLMs) as coding agents promises to accelerate software development, but their impact on generated code reproducibility remains largely unexplored. This paper presents an empirical study…