Image de couverture de livre

How and Why Agents Can Identify Bug-Introducing Commits

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Risse, Niklas, Böhme, Marcel
Format:	Preprint
Publié:	2026
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

Can LLM Generate Regression Tests for Software Commits?
par: Liu, Jing, et autres
Publié: (2025)

Identifying Bug Inducing Commits by Combining Fault Localisation and Code Change Histories
par: An, Gabin, et autres
Publié: (2025)

AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits
par: Lyu, Yunbo, et autres
Publié: (2026)

An Exploratory Study of Bug-Introducing Changes: Exploring Relationships in Bug-Introducing Changes Towards Causal Understanding
par: Schulte, Lukas, et autres
Publié: (2023)

Fundamental Challenges in Cybersecurity and a Philosophy of Vulnerability-Guided Hardening
par: Böhme, Marcel
Publié: (2024)

Investigating the Impact of Code Comment Inconsistency on Bug Introducing
par: Radmanesh, Shiva, et autres
Publié: (2024)

Fuzzing: On Benchmarking Outcome as a Function of Benchmark Properties
par: Wolff, Dylan, et autres
Publié: (2022)

AgenticSZZ: Temporal Knowledge Graph-Guided Agentic Bug-Inducing Commit Identification
par: Shi, Yu, et autres
Publié: (2026)

Confident Learning-based Network for Detecting Bug-Inducing Commits on SZZ with Noisy Labels
par: Sun, Weihao, et autres
Publié: (2026)

Detecting the Root Cause Code Lines in Bug-Fixing Commits by Heterogeneous Graph Learning
par: Ji, Liguo, et autres
Publié: (2025)

Empirical Computation
par: Tang, Eric, et autres
Publié: (2025)

Identifying Concurrency Bug Reports via Linguistic Patterns
par: Shao, Shuai, et autres
Publié: (2026)

Lost in Translation: A Study of Bugs Introduced by Large Language Models while Translating Code
par: Pan, Rangeet, et autres
Publié: (2023)

Utilizing Source Code Syntax Patterns to Detect Bug Inducing Commits using Machine Learning Models
par: Nadim, Md, et autres
Publié: (2022)

How is Testing Related to Single Statement Bugs?
par: Rahman, Habibur, et autres
Publié: (2024)

Duplicate Bug Report Detection: How Far Are We?
par: Zhang, Ting, et autres
Publié: (2022)

AFLNet Five Years Later: On Coverage-Guided Protocol Fuzzing
par: Meng, Ruijie, et autres
Publié: (2024)

Vital: Vulnerability-Oriented Symbolic Execution via Type-Unsafe Pointer-Guided Monte Carlo Tree Search
par: Tu, Haoxin, et autres
Publié: (2024)

PerfBench: Can Agents Resolve Real-World Performance Bugs?
par: Garg, Spandan, et autres
Publié: (2025)

An Empirical Study of Bugs in Modern LLM Agent Frameworks
par: Zhu, Xinxue, et autres
Publié: (2026)

CMind: An AI Agent for Localizing C Memory Bugs
par: Su, Chia-Yi, et autres
Publié: (2026)

DeepFWI: Identifying Bug-Sensitive Warnings with Multi-Modal Code-Warning Semantics
par: Liu, Han, et autres
Publié: (2024)

Bug Whispering: Towards Audio Bug Reporting
par: Masserini, Elena, et autres
Publié: (2025)

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
par: Chen, Guoxin, et autres
Publié: (2026)

Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?
par: Garg, Spandan, et autres
Publié: (2026)

When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling
par: Islam, Niful, et autres
Publié: (2026)

SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
par: Mündler, Niels, et autres
Publié: (2024)

Can AI Agents Generate Microservices? How Far are We?
par: Adnan, Bassam, et autres
Publié: (2026)

BugScope: Learn to Find Bugs Like Human
par: Guo, Jinyao, et autres
Publié: (2025)

On Interaction Effects in Greybox Fuzzing
par: Kitsios, Konstantinos, et autres
Publié: (2025)

Can GPT-O1 Kill All Bugs? An Evaluation of GPT-Family LLMs on QuixBugs
par: Hu, Haichuan, et autres
Publié: (2024)

How to Gain Commit Rights in Modern Top Open Source Communities?
par: Tan, Xin, et autres
Publié: (2024)

SelfHeal: Empirical Fix Pattern Analysis and Bug Repair in LLM Agents
par: Islam, Niful, et autres
Publié: (2026)

Characterizing Real-World Bugs in Tile Programs for Automated Bug Detection
par: Rathnasuriya, Ravishka, et autres
Publié: (2026)

Anticipating Bugs: Ticket-Level Bug Prediction and Temporal Proximity Effects
par: La Prova, Daniele, et autres
Publié: (2025)

GitBug-Java: A Reproducible Benchmark of Recent Java Bugs
par: Silva, André, et autres
Publié: (2024)

HaPy-Bug -- Human Annotated Python Bug Resolution Dataset
par: Przymus, Piotr, et autres
Publié: (2025)

Cottontail: Large Language Model-Driven Concolic Execution for Highly Structured Test Input Generation
par: Tu, Haoxin, et autres
Publié: (2025)

Can We Enhance Bug Report Quality Using LLMs?: An Empirical Study of LLM-Based Bug Report Generation
par: Acharya, Jagrit, et autres
Publié: (2025)

BugForge: Constructing and Utilizing DBMS Bug Repository to Enhance DBMS Testing
par: Li, Dawei, et autres
Publié: (2026)