Reuse or Generate? Accelerating Code Editing via Edit-Oriented Speculative Decoding

• URL: http://arxiv.org/abs/2506.02780v1
• Date: Tue, 03 Jun 2025 12:01:20 GMT
• Title: Reuse or Generate? Accelerating Code Editing via Edit-Oriented Speculative Decoding
• Abstract summary: Large Language Models (LLMs) have demonstrated remarkable capabilities in code editing, substantially enhancing software development productivity.<n>We propose EfficientEdit, a novel method that improves LLM-based code editing efficiency through two key mechanisms based on speculative decoding.<n> Experimental results show that EfficientEdit can achieve up to 10.38$times$ and 13.09$times$ speedup compared to standard autoregressive decoding.
• Score: 13.813068175559456
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in code editing, substantially enhancing software development productivity. However, the inherent complexity of code editing tasks forces existing approaches to rely on LLMs' autoregressive end-to-end generation, where decoding speed plays a critical role in efficiency. While inference acceleration techniques like speculative decoding are applied to improve the decoding efficiency, these methods fail to account for the unique characteristics of code editing tasks where changes are typically localized and existing code segments are reused. To address this limitation, we propose EfficientEdit, a novel method that improves LLM-based code editing efficiency through two key mechanisms based on speculative decoding: (1) effective reuse of original code segments while identifying potential edit locations, and (2) efficient generate edit content via high-quality drafts from edit-oriented draft models and a dynamic verification mechanism that balances quality and acceleration. Experimental results show that EfficientEdit can achieve up to 10.38$\times$ and 13.09$\times$ speedup compared to standard autoregressive decoding in CanItEdit and CodeIF-Bench, respectively, outperforming state-of-the-art inference acceleration approaches by up to 90.6%.

Related papers

• To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing [54.399335188667045]
  BlockDiff and FuncDiff are structure-aware diff formats that represent changes as block-level rewrites of syntactically coherent units.<n>AdaEdit is a general adaptive edit strategy that trains LLMs to dynamically choose the most token-efficient format between a given diff format and full code.
  arXiv  Detail & Related papers  (2026-04-30T01:14:13Z)
• SWE-Edit: Rethinking Code Editing for Efficient SWE-Agent [17.74253780030394]
  SWE-Edit decomposes code editing into two specialized subagents: a Viewer that extracts task-relevant code on demand, and an Editor that executes modifications from high-level plans.<n>On SWE-bench Verified, SWE-Edit improves resolved rate by 2.1% while reducing inference cost by 17.9%.
  arXiv  Detail & Related papers  (2026-04-28T20:35:09Z)
• Cascaded Code Editing: Large-Small Model Collaboration for Effective and Efficient Code Editing [40.309873338087975]
  We propose to decompose code editing into a two-stage cascade: textbfedit sketch generation, and textbfedit sketch application.<n>This cascaded design reduces the number of tokens generated by the large model, as the majority of the output is handled by the smaller, more efficient model.<n>The effectiveness of this approach is constrained by current small models' limited capabilities in handling long-context scenarios and cross-file dependencies.
  arXiv  Detail & Related papers  (2026-04-21T08:08:30Z)
• QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization [50.722636027998]
  Large Language Models (LLMs) achieve strong program repair performance but often suffer from over-editing.<n>We propose PRepair, a framework that mitigates over-editing and improves repair accuracy.
  arXiv  Detail & Related papers  (2026-04-07T14:56:38Z)
• Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model [98.35868970993232]
  Diffusion language models (DLMs) are emerging as a powerful and promising alternative to the dominant autoregressive paradigm.<n>We introduce efficient Sampling with Adaptive acceleration and Backtracking Enhanced Remasking (i.e., Saber) to achieve better inference speed and output quality in code generation.
  arXiv  Detail & Related papers  (2025-10-20T23:38:12Z)
• Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs [57.69190972274813]
  Diffusion Large Language Models (DLLMs) have emerged as a compelling alternative to Autoregressive models.<n>ExistingDLLMs are plagued by a severe quality-speed trade-off, where faster parallel decoding leads to significant performance degradation.<n>We introduce Wide-In, Narrow-Out (WINO), a training-free decoding algorithm that enables revokable decoding inDLLMs.
  arXiv  Detail & Related papers  (2025-07-24T16:51:33Z)
• Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
  Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
  arXiv  Detail & Related papers  (2025-05-28T17:57:47Z)
• InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing [77.47790551485721]
  In-context learning is a promising editing method by comprehending edit information through context encoding.<n>This method is constrained by the limited context window of large language models.<n>We propose InComeS, a flexible framework that enhances LLMs' ability to process editing contexts.
  arXiv  Detail & Related papers  (2025-05-28T09:20:18Z)
• In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer [42.44787022143543]
  ICEdit is an in-context editing paradigm with minimal parameter-efficient fine-tuning for quality improvement.<n>It achieves state-of-the-art editing performance with only 0.1% of the training data and 1% trainable parameters compared to previous methods.
  arXiv  Detail & Related papers  (2025-04-29T12:14:47Z)
• EditLord: Learning Code Transformation Rules for Code Editing [26.41680850940224]
  Existing approaches often formulate code editing as an implicit end-to-end task, omitting the fact that code-editing procedures inherently consist of discrete and explicit steps.<n>We introduce EditLord, a code editing framework that makes the code transformation steps explicit.<n>Our key insight is to employ a language model (LM) as an inductive learner to extract code editing rules from the training code pairs as concise meta-rule sets.
  arXiv  Detail & Related papers  (2025-03-10T16:33:59Z)
• CodeSwift: Accelerating LLM Inference for Efficient Code Generation [17.681848203476687]
  We propose CodeSwift, a highly efficient inference acceleration approach specifically designed for code generation.<n>CodeSwift constructs a multi-source datastore, providing access to both general and project-specific knowledge.<n> Experimental results show that CodeSwift can reach up to 2.53x and 2.54x speedup compared to autoregressive decoding in repository-level and standalone code generation tasks.
  arXiv  Detail & Related papers  (2025-02-24T13:30:30Z)
• LLM4EFFI: Leveraging Large Language Models to Enhance Code Efficiency and Correctness [38.399282089600284]
  Large Language Models (LLMs) have demonstrated impressive performance in code generation.<n>tool: ulineLarge ulineLanguage ulineModel for Code ulineEfficiency is a novel framework that enables LLMs to generate code that balances both efficiency and correctness.
  arXiv  Detail & Related papers  (2025-02-17T07:01:18Z)
• CodeDPO: Aligning Code Models with Self Generated and Verified Source Code [52.70310361822519]
  We propose CodeDPO, a framework that integrates preference learning into code generation to improve two key code preference factors: code correctness and efficiency. CodeDPO employs a novel dataset construction method, utilizing a self-generation-and-validation mechanism that simultaneously generates and evaluates code and test cases.
  arXiv  Detail & Related papers  (2024-10-08T01:36:15Z)
• Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion [55.0194604505437]
  Speculative decoding has emerged as a widely adopted method to accelerate large language model inference.<n>This paper proposes an adaptation of speculative decoding which uses discrete diffusion models to generate draft sequences.
  arXiv  Detail & Related papers  (2024-08-10T21:24:25Z)
• Learning Linear Block Error Correction Codes [62.25533750469467]
  We propose for the first time a unified encoder-decoder training of binary linear block codes. We also propose a novel Transformer model in which the self-attention masking is performed in a differentiable fashion for the efficient backpropagation of the code gradient.
  arXiv  Detail & Related papers  (2024-05-07T06:47:12Z)
• CodeEditorBench: Evaluating Code Editing Capability of Large Language Models [49.387195629660994]
  Large Language Models (LLMs) for code are rapidly evolving, with code editing emerging as a critical capability.<n>We introduce CodeEditorBench, an evaluation framework designed to rigorously assess the performance of LLMs in code editing tasks.<n>We curate diverse coding challenges and scenarios from five sources, covering various programming languages, complexity levels, and editing tasks.
  arXiv  Detail & Related papers  (2024-04-04T15:49:49Z)
• Exploring Data-Efficient Adaptation of Large Language Models for Code Generation [64.5583894165813]
  We propose a novel adaptation approach named DEED, which stands for Data-Efficient adaptation with Error-Driven learning for code generation.<n> Experimental results show that, compared to other mainstream fine-tuning approaches, DEED achieves superior performance with few training data.
  arXiv  Detail & Related papers  (2024-02-29T16:09:02Z)
• 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)

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.