一句话：提出无需自然语言指令、低延迟的下一编辑建议框架，用历史编辑轨迹预测编辑位置与内容。
代码编辑是软件开发中频繁且认知负担高的任务。现有 AI 辅助工具通常要求开发者显式输入自然语言指令，并存在较高延迟，容易打断开发心流，限制实际可用性。本文提出 NES（Next Edit Suggestion），一个无需指令、低延迟的代码编辑框架，通过学习历史编辑轨迹隐式捕捉开发者目标与编码习惯。NES 采用双模型架构：一个模型预测下一次编辑位置，另一个模型生成精确代码改动，二者均无需用户指令。作者基于开源的 SFT 与 DAPO 数据集训练模型，取得 75.6% 的位置准确率和 27.7% 的精确匹配率，同时将建议延迟控制在 250ms 以内。NES 已部署于蚂蚁集团，通过 Tab 键交互服务超过 20,000 名开发者，位置预测的有效接受率为 51.55%，编辑接受率为 43.44%，验证了其在实际开发工作流中的价值。
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 2, 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.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{ChenXZXLCJLD26,
title = {NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectories},
author = {Xinfang Chen and Siyang Xiao and Xianying Zhu and Junhong Xie and Ming Liang and Dajun Chen and Wei Jiang and Yong Li and Peng Di},
booktitle = {FSE},
year = {2026},
doi = {10.1145/3803437.3805244}
}