mlsanityData to 14 Oct 2026

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

arXiv 2604.05963 ↗First posted 7 Apr 2026cs.SE cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

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 fix1@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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 14 of its 22 references that are in the map. First posted on arXiv 7 Apr 2026.

Builds on

14 of 22 references.

References · 14

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  4. 2024Agentless: Demystifying LLM-based Software Engineering Agentscited by 421
  5. 2022Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generationcited by 171
  6. 2024VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Toolcited by 85
  7. 2025LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMscited by 70
  8. 2025Interactive Debugging and Steering of Multi-Agent AI Systemscited by 68
  9. 2025QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generationcited by 35
  10. 2021Automatic Program Repair with OpenAI's Codex: Evaluating QuixBugscited by 25
  11. 2024Aligning the Objective of LLM-based Program Repaircited by 12
  12. 2025HLSDebugger: Identification and Correction of Logic Bugs in HLS Code with LLM Solutionscited by 5
2 more
  1. 2025Towards LLM-based Root Cause Analysis of Hardware Design Failurescited by 4
  2. 2025SLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026When Models Edit Too Much: On the Fidelity of Minimal Code Editscited by 3
  2. 2026PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewardscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025FeedbackEval: A Benchmark for Evaluating Large Language Models in Feedback-Driven Code Repair Tasks
  2. 2026If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs
  3. 2025The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models
  4. 2026BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
  5. 2026Refine After Generation: Toward Correct and Concise Patches in LLM-based Program Repair
  6. 2025Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models
  7. 2024RePair: Automated Program Repair with Process-based Feedback
  8. 2025Enhancing Automated Program Repair via Faulty Token Localization and Quality-Aware Patch Refinement ↗