Perfagent Profiler Guided Iterative Refinement For

---
name: perfagent-profiler-guided-iterative-refinement-for
description: 'Skill generated from arXiv paper 2607.19653: PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization'
metadata:
  {
    "arxiv": {
      "id": "2607.19653",
      "title": "PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization",
      "authors": ['Ryan Deng', 'Yuanzhe Liu', 'Bastian Lipka', 'Yao Ma', 'Xuhao Chen', 'Tim Kaler', 'Jatin Ganhotra'],
      "published": "2026-07-22",
      "categories": ['cs.SE', 'cs.AI'],
      "url": "https://arxiv.org/abs/2607.19653",
      "utility": 0.97
    }
  }
---
# PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization

**arXiv:** 2607.19653  
**Published:** 2026-07-22  
**Authors:** Ryan Deng, Yuanzhe Liu, Bastian Lipka, Yao Ma, Xuhao Chen, Tim Kaler, Jatin Ganhotra  
**Categories:** cs.SE, cs.AI  
**Utility:** 0.97

## Key Innovation
Large language model (LLM) agents now perform well on correctness-oriented repository-level tasks, including SWE-Bench issue resolution and feature implementation in real codebases. However, they still struggle with repository-level code optimization, which requires preserving behavior while improving runtime performance. Passing tests is not enough in this setting; a patch must preserve behavior, implement code optimization, and approach expert speedups. Current agents often miss bottlenecks hi...

## Potential Application
This paper presents advancements that could be applied to enhance agent capabilities in the areas of cs.SE, cs.AI.

## References
- arXiv: https://arxiv.org/abs/2607.19653