Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectories

Xinfang Chen, Siyang Xiao, Xianying Zhu, Junhong Xie, Ming Liang, Dajun Chen, Wei Jiang, Yong Li, Peng Di

Abstract

Code editing is a frequent yet cognitively demanding task in software development. Existing AI-powered tools often disrupt developer flow by requiring explicit natural language instructions and suffer from high latency, limiting real-world usability. We present NES (Next Edit Suggestion), an instruction-free, low-latency code editing framework that leverages learned historical editing trajectories to implicitly capture developers' goals and coding habits. NES features a dual-model architecture: one model predicts the next edit location and the other generates the precise code change, both without any user instruction. Trained on our open-sourced SFT and DAPO datasets, NES achieves state-of-the-art performance (75.6% location accuracy, 27.7% exact match rate) while delivering suggestions in under 250ms. Deployed at Ant Group, NES serves over 20,000 developers through a seamless Tab-key interaction, achieving effective acceptance rates of 51.55% for location predictions and 43.44% for edits, demonstrating its practical impact in real-world development workflows.

NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectories

Abstract

Code editing is a frequent yet cognitively demanding task in software development. Existing AI-powered tools often disrupt developer flow by requiring explicit natural language instructions and suffer from high latency, limiting real-world usability. We present NES (Next Edit Suggestion), an instruction-free, low-latency code editing framework that leverages learned historical editing trajectories to implicitly capture developers' goals and coding habits. NES features a dual-model architecture: one model predicts the next edit location and the other generates the precise code change, both without any user instruction. Trained on our open-sourced SFT and DAPO datasets, NES achieves state-of-the-art performance (75.6% location accuracy, 27.7% exact match rate) while delivering suggestions in under 250ms. Deployed at Ant Group, NES serves over 20,000 developers through a seamless Tab-key interaction, achieving effective acceptance rates of 51.55% for location predictions and 43.44% for edits, demonstrating its practical impact in real-world development workflows.

Paper Structure

This paper contains 36 sections, 2 equations, 4 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Motivating Example
  3. Methodology
  4. An Overview of NES Framework
  5. Incremental Difference Detection
  6. High-Quality Training Dataset Construction
  7. Model Training
  8. Model Inference Optimization
  9. Incremental Difference Detection
  10. Incremental Difference Calculation
  11. Instant Difference Merge
  12. Training Dataset Construction
  13. Formulation of Sequential Edit Instances.
  14. Relevance-Based Filtering and Negative Sampling.
  15. Model Training
  16. ...and 21 more sections

Figures (4)

  • Figure 1: A motivating example of NES.
  • Figure 3: Illustration of the NES framework’s workflow.
  • Figure 4: Training dataset collection process
  • Figure 5: Input-Output Format