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

TL;DR

NES is a low-latency, instruction-free code editing framework that uses learned historical editing trajectories to predict and suggest code changes, improving developer productivity.

Contribution

It introduces a novel dual-model architecture that predicts edit locations and generates code changes without user instructions, trained on open datasets.

Findings

Achieves 75.6% location accuracy and 27.7% exact match rate.

Delivers suggestions in under 250ms.

Serves over 20,000 developers with effective acceptance rates over 50%.

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.