QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization

• URL: http://arxiv.org/abs/2604.05963v1
• Date: Tue, 07 Apr 2026 14:56:38 GMT
• Title: QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization
• Abstract summary: 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.
• Score: 50.722636027998
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) achieve strong program repair performance but often suffer from over-editing, where excessive modifications overwrite correct code and hinder bug localization. We systematically quantify its impact and introduce precise repair task, which maximizes reuse of correct code while fixing only buggy parts. Building on this insight, we propose PRepair, a framework that mitigates over-editing and improves repair accuracy. PRepair has two components: Self-Breaking, which generates diverse buggy programs via controlled bug injection and min-max sampling, and Self-Repairing, which trains models with Edit-Aware Group Relative Policy Optimization (EA-GRPO) using an edit-aware reward to encourage minimal yet correct edits. Experiments show that PRepair improves repair precision by up to 31.4% under $\mathrm{fix}_1@1$, a metric that jointly considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing, demonstrating its potential for precise and practical code repair.

Related papers

• When Models Edit Too Much: On the Fidelity of Minimal Code Edits [21.17848461238914]
  Large language models (LLMs) are increasingly used to edit existing code, but correctness alone is not enough.<n>We study over-editing, the tendency of a model to rewrite code beyond what is required to fix a bug.<n>We construct an evaluation framework from 400 BigCodeBench problems by injecting controlled AST-level corruptions into reference solutions.
  arXiv  Detail & Related papers  (2026-09-03T16:36:05Z)
• One Rewrite to Fix Them All? Type-Aware Repair Allocation for Text-to-Image Prompt Optimization [59.164665622252016]
  Text-to-image (T2I) generators often fail to follow their prompts faithfully, producing wrong counts, swapped attributes, ambiguous relations, and illegible text.<n> Prompt optimization repairs such failures by rewriting the user prompt, requiring no generator retraining, and has yielded promising results.<n>We formulate semantic prompt optimization as atomic repair allocation: each failed proposition is routed to a type-conditioned repair operator before the resulting local constraints are compiled into one executable prompt.
  arXiv  Detail & Related papers  (2026-07-21T05:31:43Z)
• Anchored Self-Play for Code Repair [68.0728003844994]
  Code repair is an important capability for language models (LMs)<n>We propose __generator--fixer self-play__, in which a single model is trained with reinforcement learning to generate bugs and fix them.<n>On BugSourceBench, we find that self-play drifts toward difficult but unrealistic bugs.<n>We propose Anchored Self-Play (ASP), which anchors self-play with a small reference set by adding a code-embedding similarity reward for generation and mixing reference bugs into fixer training.
  arXiv  Detail & Related papers  (2026-07-03T17:51:52Z)
• Specification Vibing for Automated Program Repair [8.68148153927532]
  VibeRepair is a specification-centric APR technique that treats repair as behavior-specification repair rather than ad-hoc code editing.<n>On Defects4J v1.2, VibeRepair correctly repairs 174 bugs, exceeding the strongest state-of-the-art baseline by 28 bugs.<n>On Defects4J v2.0, it repairs 178 bugs, outperforming prior approaches by 33 bugs, representing a 23% improvement.
  arXiv  Detail & Related papers  (2026-02-09T04:44:58Z)
• Specification-Guided Repair of Arithmetic Errors in Dafny Programs using LLMs [79.74676890436174]
  We present an APR tool for Dafny that uses formal specifications as oracles for fault localization and repair.<n>We localize faults through a series of steps, which include using Hoare logic to determine the state of each statement within the program.<n>Our tool achieves 89.6% fault localization coverage and GPT-4o mini yields the highest repair success rate of 74.18%.
  arXiv  Detail & Related papers  (2025-07-04T15:36:12Z)
• FastFixer: An Efficient and Effective Approach for Repairing Programming Assignments [21.848112758958543]
  We propose FastFixer, an efficient and effective approach for programming assignment repair. We first propose a novel repair-oriented fine-tuning strategy, aiming to enhance the LLM's attention towards learning how to generate the necessary patch and its associated context. Considering the repair efficiency, FastFixer achieves a remarkable inference speedup of 16.67 times compared to the autoregressive decoding algorithm.
  arXiv  Detail & Related papers  (2024-10-11T10:17:02Z)
• On The Effectiveness of Dynamic Reduction Techniques in Automated Program Repair [1.7767466724342067]
  We describe a program repair framework that effectively handles large-scale buggy programs of industrial complexity. The framework exploits program reduction in the form of program slicing to eliminate parts of the code irrelevant to the bug being repaired. Our empirical results on the widely used Defects4J dataset reveal that a substantial improvement in performance can be obtained without any degradation in repair quality.
  arXiv  Detail & Related papers  (2024-06-23T21:35:07Z)
• RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair [6.8144965833113815]
  We propose RepairLLaMA, a novel program repair approach that identifies optimal code representations for APR with fine-tuned models.<n>This results in a highly effective program repair adapter' for fixing bugs with AI.<n>Overall, RepairLLaMA correctly fixes 144 Defects4J v2, 109 HumanEval-Java, and 20 GitBug-Java bugs.
  arXiv  Detail & Related papers  (2023-12-25T11:39:46Z)
• RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair [75.40584530380589]
  We propose a novel Retrieval-Augmented Patch Generation framework (RAP-Gen) RAP-Gen explicitly leveraging relevant fix patterns retrieved from a list of previous bug-fix pairs. We evaluate RAP-Gen on three benchmarks in two programming languages, including the TFix benchmark in JavaScript, and Code Refinement and Defects4J benchmarks in Java.
  arXiv  Detail & Related papers  (2023-09-12T08:52:56Z)
• Is Self-Repair a Silver Bullet for Code Generation? [68.02601393906083]
  Large language models have shown remarkable aptitude in code generation, but still struggle to perform complex tasks. Self-repair -- in which the model debugs and repairs its own code -- has recently become a popular way to boost performance. We analyze Code Llama, GPT-3.5 and GPT-4's ability to perform self-repair on problems taken from HumanEval and APPS.
  arXiv  Detail & Related papers  (2023-06-16T15:13:17Z)
• Memory-Based Model Editing at Scale [102.28475739907498]
  Existing model editors struggle to accurately model an edit's intended scope. We propose Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model (SERAC) SERAC stores edits in an explicit memory and learns to reason over them to modulate the base model's predictions as needed.
  arXiv  Detail & Related papers  (2022-06-13T23:40:34Z)

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.