Copertina

The Limits of Long-Context Reasoning in Automated Bug Fixing

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Raju, Ravi, Ji, Mengmeng, Upasani, Shubhangi, Li, Bo, Thakker, Urmish
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Software Engineering Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On the Impact of Code Comments for Automated Bug-Fixing: An Empirical Study
di: Vitale, Antonio, et al.
Pubblicazione: (2026)

Test-Time Adaptation via Many-Shot Prompting: Benefits, Limits, and Pitfalls
di: Upasani, Shubhangi, et al.
Pubblicazione: (2026)

Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models
di: Upasani, Shubhangi, et al.
Pubblicazione: (2026)

LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference
di: Wang, Guangtao, et al.
Pubblicazione: (2025)

Combining Language and App UI Analysis for the Automated Assessment of Bug Reproduction Steps
di: Mahmud, Junayed, et al.
Pubblicazione: (2025)

Challenging Bug Prediction and Repair Models with Synthetic Bugs
di: Ibrahimzada, Ali Reza, et al.
Pubblicazione: (2023)

Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces
di: Silva, André, et al.
Pubblicazione: (2025)

SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
di: Mündler, Niels, et al.
Pubblicazione: (2024)

Whence Is A Model Fair? Fixing Fairness Bugs via Propensity Score Matching
di: Peng, Kewen, et al.
Pubblicazione: (2025)

BugGen: A Self-Correcting Multi-Agent LLM Pipeline for Realistic RTL Bug Synthesis
di: Jasper, Surya, et al.
Pubblicazione: (2025)

FGDM: Reasoning Aware Multi-Agentic Framework for Software Bug Detection using Chain of Thought and Tree of Thought Prompting
di: Padmanabhuni, Srita, et al.
Pubblicazione: (2026)

LLM Critics Help Catch LLM Bugs
di: McAleese, Nat, et al.
Pubblicazione: (2024)

An End-to-End Approach for Fixing Concurrency Bugs via SHB-Based Context Extractor
di: Li, Zhuang, et al.
Pubblicazione: (2026)

Where's the Bug? Attention Probing for Scalable Fault Localization
di: Stein, Adam, et al.
Pubblicazione: (2025)

LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs
di: Liu, Kaibo, et al.
Pubblicazione: (2024)

Towards Enhancing the Reproducibility of Deep Learning Bugs: An Empirical Study
di: Shah, Mehil B., et al.
Pubblicazione: (2024)

Language Models are Better Bug Detector Through Code-Pair Classification
di: Alrashedy, Kamel, et al.
Pubblicazione: (2023)

Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Reasoning
di: Štorek, Adam, et al.
Pubblicazione: (2025)

Bug Severity Prediction in Software Projects Using Supervised Machine Learning Models
di: Nice, Nafisha Tamanna
Pubblicazione: (2026)

When Bugs Linger: A Study of Anomalous Resolution Time Outliers and Their Themes
di: Patil, Avinash
Pubblicazione: (2025)

ARFT-Transformer: Modeling Metric Dependencies for Cross-Project Aging-Related Bug Prediction
di: Ge, Shuning, et al.
Pubblicazione: (2026)

Bug-Report-Driven Fault Localization: Industrial Benchmarking and Lesson Learned at ABB Robotics
di: Hall, Pernilla, et al.
Pubblicazione: (2026)

Constructing Domain-Specific Evaluation Sets for LLM-as-a-judge
di: Raju, Ravi, et al.
Pubblicazione: (2024)

Comparative Analysis of Quantum and Classical Support Vector Classifiers for Software Bug Prediction: An Exploratory Study
di: Nadim, Md, et al.
Pubblicazione: (2025)

Semantic GUI Scene Learning and Video Alignment for Detecting Duplicate Video-based Bug Reports
di: Yan, Yanfu, et al.
Pubblicazione: (2024)

SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair
di: Zhang, Yifan, et al.
Pubblicazione: (2026)

BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice
di: Li, Yuanpeng, et al.
Pubblicazione: (2025)

Can LLMs Find Bugs in Code? An Evaluation from Beginner Errors to Security Vulnerabilities in Python and C++
di: Mhatre, Akshay, et al.
Pubblicazione: (2025)

CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification
di: Xu, Jiacheng, et al.
Pubblicazione: (2025)

Automated Mapping of Vulnerability Advisories onto their Fix Commits in Open Source Repositories
di: Hommersom, Daan, et al.
Pubblicazione: (2021)

Automating the Training and Deployment of Models in MLOps by Integrating Systems with Machine Learning
di: Liang, Penghao, et al.
Pubblicazione: (2024)

Are Large Language Models Memorizing Bug Benchmarks?
di: Ramos, Daniel, et al.
Pubblicazione: (2024)

A Comprehensive Study of Deep Learning Model Fixing Approaches
di: You, Hanmo, et al.
Pubblicazione: (2025)

Are Sparse Autoencoders Useful for Java Function Bug Detection?
di: Melo, Rui, et al.
Pubblicazione: (2025)

Detecting the Root Cause Code Lines in Bug-Fixing Commits by Heterogeneous Graph Learning
di: Ji, Liguo, et al.
Pubblicazione: (2025)

Automating Benchmark Design
di: Dsouza, Amanda, et al.
Pubblicazione: (2025)

RepoQA: Evaluating Long Context Code Understanding
di: Liu, Jiawei, et al.
Pubblicazione: (2024)

MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair
di: Ibrahimzada, Ali Reza, et al.
Pubblicazione: (2025)

An Empirical Study on LLM-based Agents for Automated Bug Fixing
di: Meng, Xiangxin, et al.
Pubblicazione: (2024)

MarsCode Agent: AI-native Automated Bug Fixing
di: Liu, Yizhou, et al.
Pubblicazione: (2024)