arXiv Machine Learning June 10, 2026 By Nikolai Rozanov

Multi-task LLMs for Bug Classification: Efficient Inference with Auxiliary Decoding Heads

Read the original on arXiv Machine Learning →

arXiv:2606. 09956v1 Announce Type: cross Abstract: The rapid adoption of LLM-powered code generation has dramatically accelerated software development, yet effective verification methods remain severely underdeveloped.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 30

Diff-Based Code Corruption using LLMs for Large-Scale Bugfix Benchmarking

arXiv:2606. 29088v1 Announce Type: cross Abstract: There are various benchmarks to evaluate bugfixing capabilities of Large Language Models.

By Bal\'azs Szalontai, \'Abel Szauter, Bal\'azs M\'arton, P\'eter Verebics, Bal\'azs Pint\'er, Tibor Gregorics

llms fine-tuning benchmarks

arXiv Machine Learning

2d ago

From Codebase to Culprit (C2C): Reducing the Search Space for Bugs with Semantic Retrieval and Hierarchical Reinforcement Learning

arXiv:2609.38402v1 Announce Type: cross Abstract: We introduce C2C (From Codebase to Culprit), a framework for precise bug localization that progressively reduces the debugging search space across mu...

By Ankur Garg, Corey Yang-Smith, Rishav Rishav, Ahmad Abdellatif, Samira Ebrahimi Kahou

rag reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 3

BLAgent: Agentic RAG for File-Level Bug Localization

arXiv:2605. 17965v2 Announce Type: replace-cross Abstract: Bug localization remains a key bottleneck for large language model (LLM)-based software maintenance, where accurately identifying faulty code is essential for debugging, root cause analysis, triage, and automated program repair (APR).

By Md Afif Al Mamun, Gias Uddin

llms rag agents

arXiv AI

Jun 3

FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement

arXiv:2606. 03852v1 Announce Type: cross Abstract: Large language models often generate code with bugs.

By Yinsheng Yao, Hongxiang Zhang, Weixi Tong, Tianyi Zhang

llms

arXiv AI

Jun 24

JupOtter: Cell-Level Bug Detection in Jupyter Notebooks

arXiv:2606. 23877v1 Announce Type: cross Abstract: Jupyter Notebooks are an increasingly popular coding environment used across many domains, especially in Python-based data science and scientific computing.

By Lukas Ottenhof, Thibaud Lutellier

llms nlp

arXiv AI

Aug 3

RePaCA: Leveraging Reasoning Large Language Models for Static Automated Patch Correctness Assessment

arXiv:2507. 22580v2 Announce Type: replace-cross Abstract: Automated Program Repair (APR) seeks to automatically correct software bugs without requiring human intervention.

By Marcos Fuster-Pena, David de-Fitero-Dominguez, Antonio Garcia-Cabot, Eva Garcia-Lopez

llms reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

Diff-Based Code Corruption using LLMs for Large-Scale Bugfix Benchmarking

From Codebase to Culprit (C2C): Reducing the Search Space for Bugs with Semantic Retrieval and Hierarchical Reinforcement Learning

BLAgent: Agentic RAG for File-Level Bug Localization

FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement

JupOtter: Cell-Level Bug Detection in Jupyter Notebooks

RePaCA: Leveraging Reasoning Large Language Models for Static Automated Patch Correctness Assessment