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

arXiv: https://arxiv.org/abs/2508.02473 · HTML: https://mlsanity.com/paper/2508.02473/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 59 references that are in the map.
- First posted on arXiv 4 Aug 2025.

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

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [SWE-Bench+: Enhanced Coding Benchmark for LLMs](https://mlsanity.com/paper/2410.06992/) (2024)
- [ACECODER: Acing Coder RL via Automated Test-Case Synthesis](https://mlsanity.com/paper/2502.01718/) (2025)
- [ACEBench: Who Wins the Match Point in Tool Usage?](https://mlsanity.com/paper/2501.12851/) (2025)
- [Multi-task Learning based Pre-trained Language Model for Code Completion](https://mlsanity.com/paper/2012.14631/) (2020)
- [CoditT5: Pretraining for Source Code and Natural Language Editing](https://mlsanity.com/paper/2208.05446/) (2022)
- [CODIT: Code Editing with Tree-Based Neural Models](https://mlsanity.com/paper/1810.00314/) (2018)
- [REPOFUSE: Repository-Level Code Completion with Fused Dual Context](https://mlsanity.com/paper/2402.14323/) (2024)
- [InstructCoder: Instruction Tuning Large Language Models for Code Editing](https://mlsanity.com/paper/2310.20329/) (2023)
- [Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance](https://mlsanity.com/paper/2404.08817/) (2024)
- [Fixing Large Language Models' Specification Misunderstanding for Better Code Generation](https://mlsanity.com/paper/2309.16120/) (2023)
- [GrACE: Generation using Associated Code Edits](https://mlsanity.com/paper/2305.14129/) (2023)
- [Does Your Neural Code Completion Model Use My Code? A Membership Inference Approach](https://mlsanity.com/paper/2404.14296/) (2024)
- [Overwatch: Learning Patterns in Code Edit Sequences](https://mlsanity.com/paper/2207.12456/) (2022)
- [Automated Code Editing with Search-Generate-Modify](https://mlsanity.com/paper/2306.06490/) (2023)
- [Automatically Recommend Code Updates: Are We There Yet?](https://mlsanity.com/paper/2209.07048/) (2022)
- [Structural Language Models of Code](https://mlsanity.com/paper/1910.00577/) (2019)
- [A Naive Approach for Automatic Line-level Code Completion](https://mlsanity.com/paper/2402.19120/) (2024)

## Built on by (most cited first, 2 of 2)

- [Pre-Filtering Code Suggestions using Developer Behavioral Telemetry to Optimize LLM-Assisted Programming](https://mlsanity.com/paper/2511.18849/) (2025)
- [Excision Score: Evaluating Edits with Surgical Precision](https://mlsanity.com/paper/2510.21537/) (2025)

## Abstract (arXiv)

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.