paper-with-me

Program Repair

4개 벤치마크 · 논문 192편 · 이 태스크의 논문 보기 →

Benchmarks

DeepFix

결과 8개

GitHub-Python

결과 4개

HumanEvalPack

결과 2개

Most implemented

Papers

If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs

2026-09-09 · Xietao Wang-Lin, Anton Isopoussu, Louis Mahon arxiv

Large language models (LLMs) have become ubiquitous in software development, with LLM-based automated program repair tools increasingly used during code review. In this report, we explore the iterative blind use of LLMs …

Program Repair

Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair

2026-09-04 · Xuemeng Cai, Jiakun Liu, Linhan Yang, Wei Ma 외 arxiv

Large language models (LLMs) have significantly advanced automated program repair (APR), yet existing evaluations remain largely result-centric and provide limited insight into hallucination during repair. In APR, halluc…

Program Repair

Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency

2026-08-14 · Junchi Liu, Ali Bigdeli, Roya Daneshi, Atu Ambala 외 arxiv

Background: Software bugs remain a critical challenge in development, necessitating effective Automated Program Repair (APR) techniques. While Large Language Model (LLM)-based APR systems have shown promise, prior studie…

Program Repair

How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair

2026-07-28 · Ramtin Ehsani, Irene Manotas, Saurabh Pujar, Luca Buratti 외 arxiv

Large Language Model (LLM)-based Automated Program Repair systems are advancing rapidly, yet their performance remains inconsistent. Even when provided with the same contextual information, an LLM may generate a correct …

Program Repair

Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes

2026-07-22 · Yuhao Tan, Zhibang Yang, Fangkai Yang, Yuan Yao 외 arxiv

Large language models (LLMs) have made automated program repair (APR) increasingly practical for real-world bugs, but repairing directly from bug reports remains underconstrained. Bug reproduction tests (BRTs) help close…

Program Repair

Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs

2026-07-14 · Zhili Huang, Ling Xu, Hongyu Zhang arxiv

Large language models (LLMs) have improved automated program repair (APR), but two limitations remain. First, raw execution traces are often too large and repetitive to serve as effective model context. Second, repeated …

Program Repair

전체 192편 보기 →