# Automated Code Editing with Search-Generate-Modify

arXiv: https://arxiv.org/abs/2306.06490 · HTML: https://mlsanity.com/paper/2306.06490/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2023.

## Built on by (most cited first, 8 of 8)

- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Automatic Programming: Large Language Models and Beyond](https://mlsanity.com/paper/2405.02213/) (2024)
- [CigaR: Cost-efficient Program Repair with LLMs](https://mlsanity.com/paper/2402.06598/) (2024)
- [Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluation](https://mlsanity.com/paper/2508.14066/) (2025)
- [kAgent: An execution-guided crash resolution agent for the Linux kernel](https://mlsanity.com/paper/2504.20412/) (2025)
- [Next Edit Prediction: Learning to Predict Code Edits from Context and Interaction History](https://mlsanity.com/paper/2508.10074/) (2025)
- [NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectories](https://mlsanity.com/paper/2508.02473/) (2025)
- [AdaptAgent: A Multi-agent, Domain-Guided Reasoning Framework for Code Adaptation](https://mlsanity.com/paper/2608.04459/) (2026)

## Abstract (arXiv)

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.