Image de couverture de livre

Characterizing Multi-Hunk Patches: Divergence, Proximity, and LLM Repair Challenges

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Nashid, Noor, Ding, Daniel, Gallaba, Keheliya, Hassan, Ahmed E., Mesbah, Ali
Format:	Preprint
Publié:	2025
Sujets:	Software Engineering
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair
par: Nashid, Noor, et autres
Publié: (2025)

Dockerfile Flakiness: Characterization and Repair
par: Shabani, Taha, et autres
Publié: (2024)

LLM Test Generation via Iterative Hybrid Program Analysis
par: Gu, Sijia, et autres
Publié: (2025)

Towards Conversational Development Environments: Using Theory-of-Mind and Multi-Agent Architectures for Requirements Refinement
par: Gallaba, Keheliya, et autres
Publié: (2025)

Issue2Test: Generating Reproducing Test Cases from Issue Reports
par: Nashid, Noor, et autres
Publié: (2025)

Contextual API Completion for Unseen Repositories Using LLMs
par: Nashid, Noor, et autres
Publié: (2024)

Semantic Constraint Inference for Web Form Test Generation
par: Alian, Parsa, et autres
Publié: (2024)

Towards Reliable Generation of Executable Workflows by Foundation Models
par: Masoumzadeh, Sogol, et autres
Publié: (2025)

MultiMend: Multilingual Program Repair with Context Augmentation and Multi-Hunk Patch Generation
par: Gharibi, Reza, et autres
Publié: (2025)

NaviQAte: Functionality-Guided Web Application Navigation
par: Shahbandeh, Mobina, et autres
Publié: (2024)

Feature-Driven End-To-End Test Generation
par: Alian, Parsa, et autres
Publié: (2024)

SiblingRepair: Sibling-Based Multi-Hunk Repair with Large Language Models
par: Liu, Xinyu, et autres
Publié: (2026)

Building an Open AIBOM Standard in the Wild
par: Rajbahadur, Gopi Krishnan, et autres
Publié: (2025)

Rethinking Software Engineering in the Foundation Model Era: A Curated Catalogue of Challenges in the Development of Trustworthy FMware
par: Hassan, Ahmed E., et autres
Publié: (2024)

Scalable Similarity-Aware Test Suite Minimization with Reinforcement Learning
par: Gu, Sijia, et autres
Publié: (2024)

Fine-Grained Assertion-Based Test Selection
par: Gu, Sijia, et autres
Publié: (2024)

Beyond Crash-to-Patch: Patch Evolution for Linux Kernel Repair
par: Bai, Luyao, et autres
Publié: (2026)

Patch Validation in Automated Vulnerability Repair
par: Yu, Zheng, et autres
Publié: (2026)

VISCA: Inferring Component Abstractions for Automated End-to-End Testing
par: Alian, Parsa, et autres
Publié: (2025)

ITER: Iterative Neural Repair for Multi-Location Patches
par: Ye, He, et autres
Publié: (2023)

A Case Study of LLM for Automated Vulnerability Repair: Assessing Impact of Reasoning and Patch Validation Feedback
par: Kulsum, Ummay, et autres
Publié: (2024)

The Hitchhikers Guide to Production-ready Trustworthy Foundation Model powered Software (FMware)
par: Vasilevski, Kirill, et autres
Publié: (2025)

From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair
par: Li, Chenglin, et autres
Publié: (2026)

PatchRecall: Patch-Driven Retrieval for Automated Program Repair
par: Dihan, Mahir Labib, et autres
Publié: (2026)

HAFixAgent: History-Aware Program Repair Agent
par: Shi, Yu, et autres
Publié: (2025)

Accelerating Patch Validation for Program Repair with Interception-Based Execution Scheduling
par: Xiao, Yuan-An, et autres
Publié: (2023)

Automated Repair of TEE Partitioning Issues via DSL-Guided and LLM-Assisted Patching
par: Ma, Chengyan, et autres
Publié: (2026)

Evaluating Pre-Trained Models for Multi-Language Vulnerability Patching
par: Khan, Zanis Ali, et autres
Publié: (2025)

Context-Aware CodeLLM Eviction for AI-assisted Coding
par: Thangarajah, Kishanthan, et autres
Publié: (2025)

ComPass: Contrastive Learning for Automated Patch Correctness Assessment in Program Repair
par: Zhang, Quanjun, et autres
Publié: (2026)

An Empirical Study of Challenges in Machine Learning Asset Management
par: Zhao, Zhimin, et autres
Publié: (2024)

Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities
par: Chen, Simin, et autres
Publié: (2025)

Adaptive Request Scheduling for CodeLLM Serving with SLA Guarantees
par: Chang, Shi, et autres
Publié: (2025)

Enhancing Automated Program Repair via Faulty Token Localization and Quality-Aware Patch Refinement
par: Kong, Jiaolong, et autres
Publié: (2025)

When Automated Program Repair Meets Regression Testing -- An Extensive Study on 2 Million Patches
par: Lou, Yiling, et autres
Publié: (2021)

Detect--Repair--Verify for LLM-Generated Code: A Multi-Language, Multi-Granularity Empirical Study
par: Cheng, Cheng
Publié: (2026)

Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinement
par: Luo, Wenqiang, et autres
Publié: (2025)

Multi-LLM Collaboration + Data-Centric Innovation = 2x Better Vulnerability Repair
par: Zhou, Xin, et autres
Publié: (2024)

Boosting Automatic Java-to-Cangjie Translation with Multi-Stage LLM Training and Error Repair
par: Liang, Xinyue, et autres
Publié: (2026)

Challenging Bug Prediction and Repair Models with Synthetic Bugs
par: Ibrahimzada, Ali Reza, et autres
Publié: (2023)