Paper Detail

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

Changxin Ke, Rui Zhang, Jiaming Guo, Yuanbo Wen, Li Ding, Shuo Wang, Xuyuan Zhu, Xiong Peng, Di Huang, Zidong Du, Xing Hu, Qi Guo, Yunji Chen

huggingface Score 5.0

Published 2026-04-07 · First seen 2026-04-08

General AI

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 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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{ke2026qimeng,
  title = {QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization},
  author = {Changxin Ke and Rui Zhang and Jiaming Guo and Yuanbo Wen and Li Ding and Shuo Wang and Xuyuan Zhu and Xiong Peng and Di Huang and Zidong Du and Xing Hu and Qi Guo and Yunji Chen},
  year = {2026},
  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 gene},
  url = {https://huggingface.co/papers/2604.05963},
  keywords = {program repair, over-editing, precise repair task, Self-Breaking, bug injection, min-max sampling, Self-Repairing, Edit-Aware Group Relative Policy Optimization, EA-GRPO, edit-aware reward, fix\_1@1, speculative editing, decoding throughput, code available, huggingface daily},
  eprint = {2604.05963},
  archiveprefix = {arXiv},
}

Metadata

{}