An Efficient and Adaptive Next Edit Suggestion Framework with Zero Human Instructions in IDEs

• URL: http://arxiv.org/abs/2508.02473v1
• Date: Mon, 04 Aug 2025 14:37:32 GMT
• Title: An Efficient and Adaptive Next Edit Suggestion Framework with Zero Human Instructions in IDEs
• Abstract summary: We propose NES (Next Edition), a code editing framework that delivers an instruction-free and low-latency experience.<n>Built on a dual-model architecture and trained with our high-quality SFT and DAPO datasets, NES enhances productivity by understanding developer intent.<n>Our open-sourced SFT and DAPO datasets have been demonstrated to enhance the performance of open-source CodeLLMs.
• Score: 11.041668774652145
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Code editing, including modifying, refactoring, and maintaining existing code, is the most frequent task in software development and has garnered significant attention from AI-powered tools. However, existing solutions that translate explicit natural language instructions into code edits face critical limitations, such as heavy reliance on human instruction input and high latency, which hinder their effective integration into a developer's workflow. We observe that developers' habitual behaviors and coding objectives are often reflected in their historical editing patterns, making this data key to addressing existing limitations. To leverage these insights, we propose NES (Next Edit Suggestion), an LLM-driven code editing framework that delivers an instruction-free and low-latency experience. Built on a dual-model architecture and trained with our high-quality SFT and DAPO datasets, NES enhances productivity by understanding developer intent while optimizing inference to minimize latency. NES is a scalable, industry-ready solution with a continuous Tab key interaction workflow, seamlessly adopted by a FinTech company with over 20,000 developers. Evaluations on real-world datasets show NES achieves 75.6% and 81.6% accuracy in two tasks of predicting next edit locations, alongside 91.36% ES and 27.7% EMR for intent-aligned edits, outperforming SOTA models. Our open-sourced SFT and DAPO datasets have been demonstrated to enhance the performance of open-source CodeLLMs. The demonstration of NES is available at https://youtu.be/yGoyYOe6fbY.

Related papers

• Learning Project-wise Subsequent Code Edits via Interleaving Neural-based Induction and Tool-based Deduction [18.337780894895623]
  We propose TRACE, a novel subsequent code editing solution to push the boundary of scope, accuracy, and efficiency.<n>TRACE predicts subsequent edits by interleaving neural-based induction for semantic edit prediction and tool-based deduction for syntactic edit prediction.
  arXiv  Detail & Related papers  (2026-04-14T02:56:21Z)
• EditFlow: Benchmarking and Optimizing Code Edit Recommendation Systems via Reconstruction of Developer Flows [22.596319978373455]
  Large language models (LLMs) for code editing have achieved remarkable progress, yet recent empirical studies reveal a fundamental disconnect between technical accuracy and developer productivity.<n>This paper presents EditFlow, which benchmarks and optimize subsequent code edit recommendation systems through the reconstruction of developer editing flows.
  arXiv  Detail & Related papers  (2026-02-25T09:02:45Z)
• SWE-AGI: Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents [21.8776989802963]
  SWE-AGI is an open-source benchmark for evaluating end-to-end, specification-driven construction of software systems written in MoonBit.<n>Each task involves implementing 1,000-10,000 lines of core logic, corresponding to weeks or months of engineering effort for an experienced human developer.
  arXiv  Detail & Related papers  (2026-02-10T06:31:47Z)
• Evolving with AI: A Longitudinal Analysis of Developer Logs [3.7353323067733473]
  We study how sustained AI use reshapes actual daily coding practices in the long term.<n>We analyze five dimensions of workflow change: productivity, code quality, code editing, code reuse, and context switching.<n>Our results offer empirical insights into the silent restructuring of software and provide implications for designing future AI-augmented tooling.
  arXiv  Detail & Related papers  (2026-01-15T10:30:24Z)
• QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code [52.66657751895655]
  Large Language Models (LLMs) offer a compelling new paradigm: Neural Compilation.<n>This paper introduces NeuComBack, a novel benchmark dataset specifically designed for IR-to-assembly compilation.<n>We propose a self-evolving prompt optimization method that enables LLMs to evolve their internal prompt strategies.
  arXiv  Detail & Related papers  (2025-11-03T03:20:26Z)
• CodeClash: Benchmarking Goal-Oriented Software Engineering [63.65464283837602]
  We run 1680 tournaments (25,200 rounds total) to evaluate 8 LMs across 6 arenas.<n>Our results reveal that while models exhibit diverse development styles, they share fundamental limitations in strategic reasoning.<n>We open-source CodeClash to advance the study of autonomous, goal-oriented code development.
  arXiv  Detail & Related papers  (2025-11-02T07:42:51Z)
• ACE: Automated Technical Debt Remediation with Validated Large Language Model Refactorings [8.0322025529523]
  This paper introduces Augmented Code Engineering (ACE), a tool that automates code improvements using validated output.<n>Early feedback from users suggests that AI-enabled helps mitigate code-level technical debt that otherwise rarely gets acted upon.
  arXiv  Detail & Related papers  (2025-07-04T12:39:27Z)
• ORMind: A Cognitive-Inspired End-to-End Reasoning Framework for Operations Research [53.736407871322314]
  We introduce ORMind, a cognitive-inspired framework that enhances optimization through counterfactual reasoning.<n>Our approach emulates human cognition, implementing an end-to-end workflow that transforms requirements into mathematical models and executable code.<n>It is currently being tested internally in Lenovo's AI Assistant, with plans to enhance optimization capabilities for both business and consumer customers.
  arXiv  Detail & Related papers  (2025-06-02T05:11:21Z)
• DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning [57.285435980459205]
  compositional visual reasoning approaches have shown promise as more effective strategies than end-to-end VR methods.<n>We propose DWIM: Discrepancy-aware training generation, which assesses tool usage and extracts more viable for training.<n>Instruct-Masking fine-tuning, which guides the model to only clone effective actions, enabling the generation of more practical solutions.
  arXiv  Detail & Related papers  (2025-03-25T01:57:59Z)
• CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation [20.013757490442064]
  We introduce CodeIF, the first benchmark designed to assess the abilities of Large Language Models (LLMs) to adhere to task-oriented instructions.<n>CodeIF encompasses a broad range of tasks, including function synthesis, algorithmic instructions, and code explanation.<n>We conduct extensive experiments with LLMs, analyzing their strengths and limitations in meeting the demands of these tasks.
  arXiv  Detail & Related papers  (2025-02-26T14:19:49Z)
• OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models [76.59316249991657]
  Large language models (LLMs) for code have become indispensable in various domains, including code generation, reasoning tasks and agent systems.<n>While open-access code LLMs are increasingly approaching the performance levels of proprietary models, high-quality code LLMs remain limited.<n>We introduce OpenCoder, a top-tier code LLM that not only achieves performance comparable to leading models but also serves as an "open cookbook" for the research community.
  arXiv  Detail & Related papers  (2024-11-07T17:47:25Z)
• SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models [34.3296459569307]
  Large language models (LLMs) have demonstrated remarkable capabilities, but their outputs can sometimes be unreliable or factually incorrect.<n>We introduce Self Logits Evolution Decoding (SLED), a novel decoding framework that enhances the truthfulness of LLMs.<n>We show that SLED consistently improves factual accuracy by up to 20% compared to existing decoding methods.
  arXiv  Detail & Related papers  (2024-11-01T17:33:34Z)
• AIvril: AI-Driven RTL Generation With Verification In-The-Loop [0.7831852829409273]
  Large Language Models (LLMs) are computational models capable of performing complex natural language processing tasks. This paper introduces AIvril, a framework designed to enhance the accuracy and reliability of RTL-aware LLMs.
  arXiv  Detail & Related papers  (2024-09-03T15:07:11Z)
• GrACE: Generation using Associated Code Edits [23.643567386291988]
  We endowing pre-trained large language models (LLMs) of code with the knowledge of prior, relevant edits. The generative capability of the LLMs helps address the diversity in code changes and conditioning code generation on prior edits. We evaluate two well-known LLMs, Codex and CodeT5, in zero-shot and fine-tuning settings respectively.
  arXiv  Detail & Related papers  (2023-05-23T14:55:44Z)
• CodeT5+: Open Code Large Language Models for Code Understanding and Generation [72.1638273937025]
  Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. CodeT5+ is a family of encoder-decoder LLMs for code in which component modules can be flexibly combined to suit a wide range of downstream code tasks. We extensively evaluate CodeT5+ on over 20 code-related benchmarks in different settings, including zero-shot, finetuning, and instruction-tuning.
  arXiv  Detail & Related papers  (2023-05-13T14:23:07Z)
• Learning Performance-Improving Code Edits [107.21538852090208]
  We introduce a framework for adapting large language models (LLMs) to high-level program optimization. First, we curate a dataset of performance-improving edits made by human programmers of over 77,000 competitive C++ programming submission pairs. For prompting, we propose retrieval-based few-shot prompting and chain-of-thought, and for finetuning, these include performance-conditioned generation and synthetic data augmentation based on self-play.
  arXiv  Detail & Related papers  (2023-02-15T18:59:21Z)
• Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks [118.49566068398642]
  Cross-modal encoders for vision-language (VL) tasks are often pretrained with carefully curated vision-language datasets. Unimodal encoders are pretrained with simpler annotations that are less cost-prohibitive, achieving scales of hundreds of millions to billions. We propose Multimodal Adaptive Distillation (MAD), which adaptively distills useful knowledge from pretrained encoders to cross-modal VL encoders.
  arXiv  Detail & Related papers  (2022-04-22T04:41:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.