arXiv Machine Learning

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

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.

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

arXiv AI

Aug 17

Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency

arXiv:2608. 14065v1 Announce Type: cross Abstract: Background: Software bugs remain a critical challenge in development, necessitating effective Automated Program Repair (APR) techniques.

By Junchi Liu, Ali Bigdeli, Roya Daneshi, Atu Ambala, Sudipto Ghosh, Fabio Santos

llms

arXiv AI

Jul 9

AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection

arXiv:2604. 11950v2 Announce Type: replace-cross Abstract: While recent LLM-based agents can identify many candidate bugs in source code, their reports remain static hypotheses that require manual validation, limiting the practicality of automated bug detection.

By Zijie Zhao, Chenyuan Yang, Weidong Wang, Yihan Yang, Ziqi Zhang, Lingming Zhang

llms rag agents benchmarks safety

arXiv AI

Jul 2

SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests

arXiv:2607. 00990v1 Announce Type: cross Abstract: Large language model (LLM)-based software engineering agents are increasingly developed to resolve software issues by generating patches from issue reports and code repositories.

By Yaoqi Guo, Yang Liu, Jie M. Zhang, Yun Ma, Yiling Lou, Zhenpeng Chen

llms agents benchmarks

arXiv AI

Jun 16

FasterPy: An LLM-based Code Execution Efficiency Optimization Framework

arXiv:2512. 22827v2 Announce Type: replace-cross Abstract: Code often suffers from performance bugs.

By Yue Wu, Minghao Han, Ruiyin Li, Peng Liang, Amjed Tahir, Zengyang Li, Qiong Feng, Mojtaba Shahin

llms rag fine-tuning benchmarks

arXiv AI

Sep 24

Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark

The paper introduces SWE-Flux, a repository‑level benchmark designed to test large language models’ ability to reason about runtime behavior. It contains 480 execution‑grounded instances from 12 real Python repositories, with gold answers automatically harvested from instrumented test executions. Evaluation of five LLMs shows the task remains difficult, with the best model achieving only 37% accuracy, and the benchmark can generate challenging variants through input perturbation.

By Hamed Taherkhani, Mohammad Abdollahi, Melika Sepidband, Hridya Dhulipala, Tien N. Nguyen, Hadi Hemmati

llms benchmarks

arXiv Computation and Language

Sep 25

Large Language Models for Programming: Actually Fixing or Reimplementing Incorrect Code?

The paper investigates how large language models (LLMs) handle bug fixing versus problem solving in competitive programming. Using a dataset of ~3,000 Codeforces submissions and their human fixes, the authors compare LLM-generated patches to human patches and assess whether LLMs prefer to modify buggy code or generate new solutions. Results show that LLMs often alter more lines than necessary and sometimes produce entirely new solutions, performing better when allowed to generate solutions from scratch rather than patching existing code.

By Alexandru Stefan Stoica, Traian Rebedea, Marian Cristian Mihaescu

llms safety

Related stories