Starcoder 2 and the stack v2: The next generation

A Lozhkov, R Li, LB Allal, F Cassano… - arXiv preprint arXiv …, 2024 - arxiv.org
The BigCode project, an open-scientific collaboration focused on the responsible
development of Large Language Models for Code (Code LLMs), introduces StarCoder2. In …

The Widening Gap: The Benefits and Harms of Generative AI for Novice Programmers

J Prather, BN Reeves, J Leinonen, S MacNeil… - Proceedings of the …, 2024 - dl.acm.org
Novice programmers often struggle through programming problem solving due to a lack of
metacognitive awareness and strategies. Previous research has shown that novices can …

Creativity, Generative AI, and Software Development: A Research Agenda

V Jackson, B Vasilescu, D Russo, P Ralph… - arXiv preprint arXiv …, 2024 - arxiv.org
Creativity has always been considered a major differentiator to separate the good from the
great, and we believe the importance of creativity for software development will only …

Benchmarks and Metrics for Evaluations of Code Generation: A Critical Review

DG Paul, H Zhu, I Bayley - arXiv preprint arXiv:2406.12655, 2024 - arxiv.org
With the rapid development of Large Language Models (LLMs), a large number of machine
learning models have been developed to assist programming tasks including the generation …

Rethinking Software Engineering in the Foundation Model Era: From Task-Driven AI Copilots to Goal-Driven AI Pair Programmers

AE Hassan, GA Oliva, D Lin, B Chen, Z Ming - arXiv preprint arXiv …, 2024 - arxiv.org
The advent of Foundation Models (FMs) and AI-powered copilots has transformed the
landscape of software development, offering unprecedented code completion capabilities …

Exploring the problems, their causes and solutions of AI pair programming: A study on GitHub and Stack Overflow

X Zhou, P Liang, B Zhang, Z Li, A Ahmad… - Journal of Systems and …, 2025 - Elsevier
With the recent advancement of Artificial Intelligence (AI) and Large Language Models
(LLMs), AI-based code generation tools become a practical solution for software …

Statically Contextualizing Large Language Models with Typed Holes

A Blinn, X Li, JH Kim, C Omar - arXiv preprint arXiv:2409.00921, 2024 - arxiv.org
Large language models (LLMs) have reshaped the landscape of program synthesis.
However, contemporary LLM-based code completion systems often hallucinate broken code …

The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines

M Martinez - arXiv preprint arXiv:2408.01050, 2024 - arxiv.org
The recent surge of open-source large language models (LLMs) enables developers to
create AI-based solutions while maintaining control over aspects such as privacy and …

Requirements are All You Need: The Final Frontier for End-User Software Engineering

D Robinson, C Cabrera, AD Gordon… - arXiv preprint arXiv …, 2024 - arxiv.org
What if end users could own the software development lifecycle from conception to
deployment using only requirements expressed in language, images, video or audio? We …

What Guides Our Choices? Modeling Developers' Trust and Behavioral Intentions Towards GenAI

R Choudhuri, B Trinkenreich, R Pandita… - arXiv preprint arXiv …, 2024 - arxiv.org
Generative AI (genAI) tools, such as ChatGPT or Copilot, are advertised to improve
developer productivity and are being integrated into software development. However …