Automatic programming: Large language models and beyond

MR Lyu, B Ray, A Roychoudhury, SH Tan… - ACM Transactions on …, 2024 - dl.acm.org
Automatic programming has seen increasing popularity due to the emergence of tools like
GitHub Copilot which rely on Large Language Models (LLMs). At the same time …

Cigar: Cost-efficient program repair with llms

D Hidvégi, K Etemadi, S Bobadilla… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLM) have proven to be effective at automated program repair
(APR). However, using LLMs can be highly costly, with companies invoicing users by the …

Automated commit intelligence by pre-training

S Liu, Y Li, X Xie, W Ma, G Meng, Y Liu - ACM Transactions on Software …, 2024 - dl.acm.org
GitHub commits, which record the code changes with natural language messages for
description, play a critical role in software developers' comprehension of software evolution …

Fine-Tuning Large Language Models for Practical Software Engineering: Case Studies in Automated Patch Generation

J Zhou - 2024 - gupea.ub.gu.se
In recent years, software development has become increasingly complex, posing challenges
in problem-solving, code optimization, and error correction. The rise of Artificial Intelligence …

[PDF][PDF] Reasoning for Repository-level Code Editing

A Kovrigin - alexkovrigin.me
In this work, we explore Large Language Model-based context retrieval strategies for
repository-level code editing task. To achieve this goal, we first implemented a novel code …

[PDF][PDF] Efficient Exploration and Analysis of Program Repair Search Spaces

KE SOMEOLIAYI - diva-portal.org
The ubiquitous presence of software has made its failures a huge source of cost. To avoid
this cost, fixing buggy programs is essential. As manual bug fixing, also known as …