How Do Agentic AI Systems Address Performance Optimizations? A BERTopic-Based Analysis of Pull Requests

arXiv 2512.24630 ↗First posted 31 Dec 2025cs.SEcited by 1

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

LLM-based software engineering is influencing modern software development. In addition to correctness, prior studies have also examined the performance of software artifacts generated by AI agents. However, it is unclear how exactly the agentic AI systems address performance concerns in practice. In this paper, we present an empirical study of performance-related pull requests generated by AI agents. Using LLM-assisted detection and BERTopic-based topic modeling, we identified 52 performance-related topics grouped into 10 higher-level categories. Our results show that AI agents apply performance optimizations across diverse layers of the software stack and that the type of optimization significantly affects pull request acceptance rates and review times. We also found that performance optimization by AI agents primarily occurs during the development phase, with less focus on the maintenance phase. Our findings provide empirical evidence that can support the evaluation and improvement of agentic AI systems with respect to their performance optimization behaviors and review outcomes.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 13 of its 43 references that are in the map. First posted on arXiv 31 Dec 2025.

Builds on

13 of 43 references.

Closest ancestors · 1

Same direction, newest first

2025On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub18 Sep

Other references · 12

2021Evaluating Large Language Models Trained on Codecited by 8,053
2022Large Language Models are Zero-Shot Reasonerscited by 4,323
2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
2023Towards an Understanding of Large Language Models in Software Engineering Taskscited by 67
2024A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languagescited by 65
2024A Performance Study of LLM-Generated Code on Leetcodecited by 48
2024PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedbackcited by 22
2025On the Effectiveness of LLM-as-a-judge for Code Generation and Summarizationcited by 17
2025A Taxonomy of Inefficiencies in LLM-Generated Python Codecited by 8
2025Performance Review on LLM for solving leetcode problemscited by 5
2025LLM Benchmarking with LLaMA2: Evaluating Code Development Performance Across Multiple Programming Languagescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

2026What Do AI Agents Actually Change? An Empirical Taxonomy of Mutation Patterns in Performance-Improving Pull Requestscited by 0

Similar, not cited

Close in wording, no citation either way