# Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing

arXiv: https://arxiv.org/abs/2305.18584 · HTML: https://mlsanity.com/paper/2305.18584/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 29 May 2023.

## Builds on (most cited first, 28 of 28)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [Unified Pre-training for Program Understanding and Generation](https://mlsanity.com/paper/2103.06333/) (2021)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [SantaCoder: don't reach for the stars!](https://mlsanity.com/paper/2301.03988/) (2023)
- [CM3: A Causal Masked Multimodal Model of the Internet](https://mlsanity.com/paper/2201.07520/) (2022)
- [Towards Automating Code Review Activities](https://mlsanity.com/paper/2101.02518/) (2021)
- [CoditT5: Pretraining for Source Code and Natural Language Editing](https://mlsanity.com/paper/2208.05446/) (2022)
- [LambdaNet: Probabilistic Type Inference using Graph Neural Networks](https://mlsanity.com/paper/2005.02161/) (2020)
- [Code Translation with Compiler Representations](https://mlsanity.com/paper/2207.03578/) (2022)
- [CODIT: Code Editing with Tree-Based Neural Models](https://mlsanity.com/paper/1810.00314/) (2018)
- [Fast and Memory-Efficient Neural Code Completion](https://mlsanity.com/paper/2004.13651/) (2020)
- [TypeWriter: Neural Type Prediction with Search-based Validation](https://mlsanity.com/paper/1912.03768/) (2019)
- [Learning to Update Natural Language Comments Based on Code Changes](https://mlsanity.com/paper/2004.12169/) (2020)
- [Learning to Model Editing Processes](https://mlsanity.com/paper/2205.12374/) (2022)
- [Learning to Complete Code with Sketches](https://mlsanity.com/paper/2106.10158/) (2021)
- [Copy that! Editing Sequences by Copying Spans](https://mlsanity.com/paper/2006.04771/) (2020)
- [TypeT5: Seq2seq Type Inference using Static Analysis](https://mlsanity.com/paper/2303.09564/) (2023)
- [SOAR: A Synthesis Approach for Data Science API Refactoring](https://mlsanity.com/paper/2102.06726/) (2021)
- [Learning to Describe Solutions for Bug Reports Based on Developer Discussions](https://mlsanity.com/paper/2110.04353/) (2021)

## Built on by (most cited first, 9 of 9)

- [OctoPack: Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2308.07124/) (2023)
- [Agents in Software Engineering: Survey, Landscape, and Vision](https://mlsanity.com/paper/2409.09030/) (2024)
- [You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects](https://mlsanity.com/paper/2412.10133/) (2024)
- [InstructCoder: Instruction Tuning Large Language Models for Code Editing](https://mlsanity.com/paper/2310.20329/) (2023)
- [Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases](https://mlsanity.com/paper/2405.19581/) (2024)
- [CursorCore: Assist Programming through Aligning Anything](https://mlsanity.com/paper/2410.07002/) (2024)
- [Learning to Commit: Generating Organic Pull Requests via Online Repository Memory](https://mlsanity.com/paper/2603.26664/) (2026)
- [Treefix: Enabling Execution with a Tree of Prefixes](https://mlsanity.com/paper/2501.12339/) (2025)
- [Pull Requests as a Training Signal for Repo-Level Code Editing](https://mlsanity.com/paper/2602.07457/) (2026)

## Abstract (arXiv)

Developers often dedicate significant time to maintaining and refactoring existing code. However, most prior work on generative models for code focuses solely on creating new code, overlooking the distinctive needs of editing existing code. In this work, we explore a multi-round code auto-editing setting, aiming to predict edits to a code region based on recent changes within the same codebase. Our model, Coeditor, is a fine-tuned language model specifically designed for code editing tasks. We represent code changes using a line diff format and employ static analysis to form large customized model contexts, ensuring the availability of appropriate information for prediction. We collect a code editing dataset from the commit histories of 1650 open-source Python projects for training and evaluation. In a simplified single-round, single-edit task, Coeditor significantly outperforms GPT-3.5 and SOTA open-source code completion models (bringing exact-match accuracy from 34.7 up to 60.4), demonstrating the benefits of incorporating editing history for code completion. In a multi-round, multi-edit setting, we observe substantial gains by iteratively conditioning on additional user edits. We have open-sourced our code, data, and model weights to encourage future research and have released a VSCode extension powered by our model for interactive IDE usage.