# How Do Agents Perform Code Optimization? An Empirical Study

arXiv: https://arxiv.org/abs/2512.21757 · HTML: https://mlsanity.com/paper/2512.21757/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 46 references that are in the map.
- First posted on arXiv 25 Dec 2025.

## Builds on (most cited first, 7 of 7)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub](https://mlsanity.com/paper/2509.14745/) (2025)
- [Can LLMs Replace Manual Annotation of Software Engineering Artifacts?](https://mlsanity.com/paper/2408.05534/) (2024)
- [Unveiling ChatGPT's Usage in Open Source Projects: A Mining-based Study](https://mlsanity.com/paper/2402.16480/) (2024)
- [Language Models for Code Optimization: Survey, Challenges and Future Directions](https://mlsanity.com/paper/2501.01277/) (2025)
- [RAPGen: An Approach for Fixing Code Inefficiencies in Zero-Shot](https://mlsanity.com/paper/2306.17077/) (2023)
- [SysLLMatic: Large Language Models are Software System Optimizers](https://mlsanity.com/paper/2506.01249/) (2025)

## Built on by (most cited first, 4 of 4)

- [Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?](https://mlsanity.com/paper/2607.01211/) (2026)
- [What Do AI Agents Actually Change? An Empirical Taxonomy of Mutation Patterns in Performance-Improving Pull Requests](https://mlsanity.com/paper/2607.05666/) (2026)
- [Model-Based Agentic Software Engineering](https://mlsanity.com/paper/2608.25174/) (2026)
- [Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization](https://mlsanity.com/paper/2609.14839/) (2026)

## Abstract (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.