English

Automated Code Editing with Search-Generate-Modify

Software Engineering 2024-02-27 v2 Programming Languages

Abstract

Code editing is essential in evolving software development. Many automated code editing tools have been proposed that leverage both Information Retrieval-based techniques and Machine Learning-based code generation and code editing models. Each technique comes with its own promises and perils, and they are often used together to complement their strengths and compensate for their weaknesses. This paper proposes a hybrid approach to better synthesize code edits by leveraging the power of code search, generation, and modification. Our key observation is that a patch obtained by search and retrieval, even if imperfect, can provide helpful guidance to a code generation model. However, a retrieval-guided patch produced by a code generation model can still be a few tokens off from the intended patch. Such generated patches can be slightly modified to create the intended patches. SARGAM is a novel tool designed to mimic a real developer's code editing behavior. Given an original code version, the developer may search for related patches, generate or write the code, and then modify the generated code to adapt it to the right context. Our evaluation of SARGAM on edit generation shows superior performance with respect to current state-of-the-art techniques. SARGAM also shows great effectiveness on automated program repair tasks.

Keywords

Cite

@article{arxiv.2306.06490,
  title  = {Automated Code Editing with Search-Generate-Modify},
  author = {Changshu Liu and Pelin Cetin and Yogesh Patodia and Saikat Chakraborty and Yangruibo Ding and Baishakhi Ray},
  journal= {arXiv preprint arXiv:2306.06490},
  year   = {2024}
}

Comments

12 pages, 10 figures

R2 v1 2026-06-28T11:02:00.618Z