# Identifying Performance-Sensitive Configurations in Software Systems through Code Analysis with LLM Agents

arXiv: https://arxiv.org/abs/2406.12806 · HTML: https://mlsanity.com/paper/2406.12806/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 59 references that are in the map.
- First posted on arXiv 18 Jun 2024.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 14 of 14)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023)
- [An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation](https://mlsanity.com/paper/2302.06527/) (2023)
- [Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code](https://mlsanity.com/paper/2404.00971/) (2024)
- [No More Manual Tests? Evaluating and Improving ChatGPT for Unit Test Generation](https://mlsanity.com/paper/2305.04207/) (2023)
- [Face It Yourselves: An LLM-Based Two-Stage Strategy to Localize Configuration Errors via Logs](https://mlsanity.com/paper/2404.00640/) (2024)
- [Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning](https://mlsanity.com/paper/2002.10198/) (2020)
- [How to Refactor this Code? An Exploratory Study on Developer-ChatGPT Refactoring Conversations](https://mlsanity.com/paper/2402.06013/) (2024)
- [On Debugging the Performance of Configurable Software Systems: Developer Needs and Tailored Tool Support](https://mlsanity.com/paper/2203.10356/) (2022)

## Built on by (most cited first, 2 of 2)

- [Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crews](https://mlsanity.com/paper/2502.05439/) (2025)
- [A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards](https://mlsanity.com/paper/2505.13766/) (2025)

## Abstract (arXiv)

Configuration settings are essential for tailoring software behavior to meet specific performance requirements. However, incorrect configurations are widespread, and identifying those that impact system performance is challenging due to the vast number and complexity of possible settings. In this work, we present PerfSense, a lightweight framework that leverages Large Language Models (LLMs) to efficiently identify performance-sensitive configurations with minimal overhead. PerfSense employs LLM agents to simulate interactions between developers and performance engineers using advanced prompting techniques such as prompt chaining and retrieval-augmented generation (RAG). Our evaluation of seven open-source Java systems demonstrates that PerfSense achieves an average accuracy of 64.77% in classifying performance-sensitive configurations, outperforming both our LLM baseline (50.36%) and the previous state-of-the-art method (61.75%). Notably, our prompt chaining technique improves recall by 10% to 30% while maintaining similar precision levels. Additionally, a manual analysis of 362 misclassifications reveals common issues, including LLMs' misunderstandings of requirements (26.8%). In summary, PerfSense significantly reduces manual effort in classifying performance-sensitive configurations and offers valuable insights for future LLM-based code analysis research.