代码大模型 / AI 编程

How Effective Are Neural Networks for Fixing Security Vulnerabilities

Yi Wu, Nan Jiang, Hung Viet Pham, Thibaud Lutellier, Jordan Davis, Lin Tan, Petr Babkin, Sameena Shah

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.AI

Comments This paper was accepted in the proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2023), and was presented at the conference, that was held in Seattle, USA, 17-21 July 2023

Code Security Vulnerability Repair Using Reinforcement Learning with Large Language Models

Nafis Tanveer Islam, Mohammad Bahrami Karkevandi, Peyman Najafirad

专题命中 程序修复 ：code generation(abstract)；分类 cs.SE、cs.AI

On Repairing Quantum Programs Using ChatGPT

Xiaoyu Guo, Jianjun Zhao, Pengzhan Zhao

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.PL

Comments The 5th International Workshop on Quantum Software Engineering (Q-SE 2024)

AdaptivePaste: Code Adaptation through Learning Semantics-aware Variable Usage Representations

Xiaoyu Liu, Jinu Jang, Neel Sundaresan, Miltiadis Allamanis, Alexey Svyatkovskiy

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.CL

Frustrated with Code Quality Issues? LLMs can Help!

Nalin Wadhwa, Jui Pradhan, Atharv Sonwane, Surya Prakash Sahu, Nagarajan Natarajan, Aditya Kanade, Suresh Parthasarathy, Sriram Rajamani

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.AI

Better patching using LLM prompting, via Self-Consistency

Toufique Ahmed, Premkumar Devanbu

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.LG

Comments Accepted at ASE-NIER (2023) track

Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning

Thanh Le-Cong, Duc-Minh Luong, Xuan Bach D. Le, David Lo, Nhat-Hoa Tran, Bui Quang-Huy, Quyet-Thang Huynh

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.LG

Journal ref IEEE Transactions on Software Engineering, 2023

Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5

Nghi D. Q. Bui, Yue Wang, Steven Hoi

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.CL

Comments Accepted to EMNLP 2022 Findings Track

Repairing Bugs in Python Assignments Using Large Language Models

Jialu Zhang, José Cambronero, Sumit Gulwani, Vu Le, Ruzica Piskac, Gustavo Soares, Gust Verbruggen

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.AI

BED: A Real-Time Object Detection System for Edge Devices

Guanchu Wang, Zaid Pervaiz Bhat, Zhimeng Jiang, Yi-Wei Chen, Daochen Zha, Alfredo Costilla Reyes, Afshin Niktash, Gorkem Ulkar, Erman Okman, Xuanting Cai, Xia Hu

专题命中 程序修复 ：repository(abstract)；分类 cs.AI、cs.LG

Mapping the Structure and Evolution of Software Testing Research Over the Past Three Decades

Alireza Salahirad, Gregory Gay, Ehsan Mohammadi

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.LG

Comments To appear, Journal of Systems and Software

Enabling Automatic Repair of Source Code Vulnerabilities Using Data-Driven Methods

Anastasiia Grishina

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.LG

Comments Accepted for the ICSE '22 Doctoral Symposium

TSSB-3M: Mining single statement bugs at massive scale

Cedric Richter, Heike Wehrheim

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.PL

Comments 7 pages, 2 figures

Data-Driven AI Model Signal-Awareness Enhancement and Introspection

Sahil Suneja, Yufan Zhuang, Yunhui Zheng, Jim Laredo, Alessandro Morari

专题命中 程序修复 ：code model(abstract)；分类 cs.SE、cs.AI

Comments Fixed author email ids

DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons

Dawn Drain, Colin B. Clement, Guillermo Serrato, Neel Sundaresan

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.LG

Exploring Plausible Patches Using Source Code Embeddings in JavaScript

Viktor Csuvik, Dániel Horváth, Márk Lajkó, László Vidács

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.AI

Comments Paper accepted in APR2021 conference

SCELMo: Source Code Embeddings from Language Models

Rafael - Michael Karampatsis, Charles Sutton

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.LG

Comments 12 pages

How Often Do Single-Statement Bugs Occur? The ManySStuBs4J Dataset

Rafael-Michael Karampatsis, Charles Sutton

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.PL

Comments 5 pages; to appear in Proceedings of MSR 2020

Using Dynamic Analysis to Generate Disjunctive Invariants

ThanhVu Nguyen, Deepak Kapur, Westley Weimer, Stephanie Forrest

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.PL

Comments appear in ICSE 2014

Estimating defectiveness of source code: A predictive model using GitHub content

Ritu Kapur, Balwinder Sodhi

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.LG

Comments Submitted to ACM ESEC/FSE 2018. Keywords: Maintaining software; Source code mining; Software defect identification; Automated software engineering; AI in software engineering

Data-Driven Feedback Generation for Introductory Programming Exercises

Ke Wang, RIshabh Singh, Zhendong Su

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.PL

Comments 12 pages

TraceDiff: Debugging Unexpected Code Behavior Using Trace Divergences

Ryo Suzuki, Gustavo Soares, Andrew Head, Elena Glassman, Ruan Reis, Melina Mongiovi, Loris D'Antoni, Bjoern Hartmann

专题命中 程序修复 ：program synthesis(abstract)；分类 cs.SE、cs.PL

Comments VL/HCC 2017

SmartPaste: Learning to Adapt Source Code

Miltiadis Allamanis, Marc Brockschmidt

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE、cs.LG

On-the-fly Query-Based Debugging with Examples

Raimondas Lencevicius

专题命中 程序修复 ：code generation(abstract)；分类 cs.SE、cs.PL

Comments In M. Ducasse (ed), proceedings of the Fourth International Workshop on Automated Debugging (AADEBUG 2000), August 2000, Munich. cs.SE/0010035 14 pages, 6 figures

AI Code Sandboxes: A Comparative Security Study. Part 1 of 2 -- Engine-Level Properties (Attack Surface, Leakage, Stackability, CVE History, Patch Cadence, Fuzzing)

AI 代码沙箱：比较安全研究。第 1 部分（共 2 部分）——引擎级属性（攻击面、泄露、可堆叠性、CVE 历史、补丁节奏、模糊测试）

George Andronchik, Pavel Lokhmakov

机构 * orbitalab.dev（orbitalab实验室） ； fellows.tech（fellows技术） 纠错

专题命中 程序修复 ：repository(abstract,comments)；分类 cs.AI

AI总结 本文通过六项引擎级测量，比较五种 AI 沙箱产品隔离访客代码与主机内核的能力，发现引擎类在架构轴上清晰分离，但产品内无差异；补丁策略是主要操作变量；模糊测试投资分为三层，最强组合（微VM × 持续公共模糊测试）空缺。

Comments 61 pages, 7 figures, 33 tables; Part 1 of 2; companion code repository (Apache-2.0): https://github.com/orbitalab/RnD-ai-sandboxes-sec-study-part-1

BloomAPR: A Bloom's Taxonomy-based Framework for Assessing the Capabilities of LLM-Powered APR Solutions

BloomAPR：基于布鲁姆教育目标分类学的框架，用于评估大语言模型驱动的自动程序修复（APR）方案的能力

Yinghang Ma, Jiho Shin, Leuson Da Silva, Zhen Ming, Jiang, Song Wang, Foutse Khomh, Shin Hwei Tan

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE

AI总结 BloomAPR是基于布鲁姆教育目标分类学的动态评估框架，评估了ChatRepair、CigaR等APR方案在不同LLM及布鲁姆分类层级下的漏洞修复能力，发现其存在性能差异并指出基准演进的必要性。

Comments 22 pages, 7 figures, Manuscript submitted to ACM Transactions on Software Engineering and Methodology

PITMuS: A Tool for Automated Bug Dataset Generation via Source-Level Mutant Reconstruction

PITMuS: 通过源级变异体重建实现自动化bug数据集生成工具

Tasfia Tasnim, Soneya Binta Hossain

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE

AI总结 本文提出PITMuS工具，通过源级变异体重建生成自动化bug数据集，解决现有工具生成的变异体难以复现和利用的问题，为bug定位和修复技术提供结构化数据支持。

Large Language Models for Fault Localization: An Empirical Study

用于故障定位的大语言模型：一项实证研究

Yingjian Xiao, Weiwei Gong, Jianjun Huang, Rongqun Hu, Hongwei Li, Anquan Jie, Boyang Yang

专题命中 程序修复 ：program repair(abstract)；分类 cs.SE

AI总结 本文通过在HumanEval-Java、Defects4J数据集上评估四款LLMs，对比非LLM基线，分析不同提示策略，明确其在语句级故障定位的优缺与实际权衡，为软件工程应用提供实证支持。

READU: Inconsistency-Driven Just-in-Time Detection and Repair of README Bugs

READU：README 错误的不一致驱动即时检测与修复

Doehyun Baek, Kilian Krampf, Michael Pradel

专题命中 程序修复 ：repository(abstract)；分类 cs.SE

AI总结 研究针对仓库级文档 README 错误，提出不一致驱动技术 READU，通过高召回率提交过滤器、并行一致性检查器等方法，能即时检测并修复错误，在六个流行仓库的提交测试中表现良好，检测到多个真阳性并成功修复部分错误。

A Single Patch Is Not Enough: Deterministic Fusion of Repair Candidates

单个补丁不够：修复候选的确定性融合

Boyang Yang, Xiangliang Hu, Luyao Ren, Yanjun Chen, Bach Le, Tegawendé F. Bissyandé, Haoye Tian

专题命中 程序修复 ：coding agent(abstract)；分类 cs.SE

AI总结 针对代码修复中候选补丁池的“pass@k到pass@1”差距，提出PatchFusion方法，通过确定性原子证据融合选择并构造最终补丁，无需测试结果，在三个基准上优于现有选择器。