paper-with-me

Papers

Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?

2026-04-19 · Wang Bill Zhu, Miaosen Chai, Shangshang Wang, Yejia Liu, Song Bian, Honghua Dong, Willie Neiswanger, Robin Jia arxiv

Unlike code completion, debugging requires localizing faults and applying targeted edits. We observe that frontier LLMs often regenerate correct but over-edited solutions during debugging. To evaluate how far LLMs are from precise debugging, we introduce the Precise Debugging Benchmark (PDB) framework, which automatically converts any coding dataset into a debugging benchmark with precision-aware evaluation. PDB generates buggy programs by synthesizing verified atomic bugs and composing them into multi-bug programs. We define two novel metrics, edit-level precision and bug-level recall, which measures how many necessary edits are made and how many bugs are resolved. We release two evaluation benchmarks: PDB-Single-Hard on single-line bugs, and PDB-Multi on multi-line bugs. Experiments show that frontier models, such as GPT-5.1-Codex and DeepSeek-V3.2-Thinking, achieve unit-test pass rates above 76% but exhibit precision below 45%, even when explicitly instructed to perform minimal debugging. Finally, we show that iterative and agentic debugging strategies do not substantially improve precision or recall, highlighting the need to rethink post-training pipelines for coding models.

📄 PDF Abstract BibTeX arXiv:2604.17338

Code (0)

등록된 구현이 없습니다.

Tasks

Code Completion

Similar Papers 제목 키워드 기반

MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios

2025-06-15 · Jinyang Huang, Xiachong Feng, Qiguang Chen, Hanjie Zhao 외

Code debugging is a crucial task in software engineering, which attracts increasing attention. While remarkable success has been made in the era of large language models (LLMs), current research still focuses on the simp…

Benchmarking

Hear Your Code Fail, Voice-Assisted Debugging for Python

2025-07-20 · Sayed Mahbub Hasan Amiri, Md. Mainul Islam, Mohammad Shakhawat Hossen, Sayed Majhab Hasan Amiri 외

This research introduces an innovative voice-assisted debugging plugin for Python that transforms silent runtime errors into actionable audible diagnostics. By implementing a global exception hook architecture with pytts…

CPUMedical Diagnosistext-to-speechText to Speech

COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis

2024-08-09 · Weiqing Yang, Hanbin Wang, Zhenghao Liu, Xinze Li 외

Code debugging is a vital stage of software development, essential for ensuring the reliability and performance of Large Language Models (LLMs) in the code generation task. Human debugging typically follows a multi-stage…

Code GenerationCode Repair

MdEval: Massively Multilingual Code Debugging

2024-11-04 · Shukai Liu, Linzheng Chai, Jian Yang, Jiajun Shi 외

Code large language models (LLMs) have made significant progress in code debugging by directly generating the correct code based on the buggy code snippet. Programming benchmarks, typically consisting of buggy code snipp…

Program Repair

DebugBench: Evaluating Debugging Capability of Large Language Models

2024-01-09 · Runchu Tian, Yining Ye, Yujia Qin, Xin Cong 외

Large Language Models (LLMs) have demonstrated exceptional coding capability. However, as another critical component of programming proficiency, the debugging capability of LLMs remains relatively unexplored. Previous ev…

Code Generation