Software engineering education in the era of conversational AI: current trends and future directions

C Sengul, R Neykova, G Destefanis - Frontiers in Artificial Intelligence, 2024 - frontiersin.org
The developments in conversational AI raised urgent questions about the future direction of
many aspects of society, including computing education. The first reactions to the fast-paced …

Llm for test script generation and migration: Challenges, capabilities, and opportunities

S Yu, C Fang, Y Ling, C Wu… - 2023 IEEE 23rd …, 2023 - ieeexplore.ieee.org
This paper investigates the application of large language models (LLM) in the domain of
mobile application test script generation. Test script generation is a vital component of …

Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving

Y Zhong, S Liu, J Chen, J Hu, Y Zhu, X Liu, X Jin… - arXiv preprint arXiv …, 2024 - arxiv.org
DistServe improves the performance of large language models (LLMs) serving by
disaggregating the prefill and decoding computation. Existing LLM serving systems colocate …

Understanding the Human-LLM Dynamic: A Literature Survey of LLM Use in Programming Tasks

D Etsenake, M Nagappan - arXiv preprint arXiv:2410.01026, 2024 - arxiv.org
Large Language Models (LLMs) are transforming programming practices, offering significant
capabilities for code generation activities. While researchers have explored the potential of …

If At First You Don't Succeed, Try, Try, Again...? Insights and LLM-informed Tooling for Detecting Retry Bugs in Software Systems

BA Stoica, U Sethi, Y Su, C Zhou, S Lu, J Mace… - Proceedings of the …, 2024 - dl.acm.org
Retry---the re-execution of a task on failure---is a common mechanism to enable resilient
software systems. Yet, despite its commonality and long history, retry remains difficult to …

A comparative analysis of large language models for code documentation generation

SS Dvivedi, V Vijay, SLR Pujari, S Lodh… - Proceedings of the 1st …, 2024 - dl.acm.org
This paper presents a comprehensive comparative analysis of Large Language Models
(LLMs) for generation of code documentation. Code documentation is an essential part of …

Formalizing natural language intent into program specifications via large language models

M Endres, S Fakhoury, S Chakraborty… - arXiv preprint arXiv …, 2023 - arxiv.org
Informal natural language that describes code functionality, such as code comments or
function documentation, may contain substantial information about a programs intent …

Pydex: Repairing bugs in introductory python assignments using llms

J Zhang, JP Cambronero, S Gulwani, V Le… - Proceedings of the …, 2024 - dl.acm.org
Students often make mistakes in their introductory programming assignments as part of their
learning process. Unfortunately, providing custom repairs for these mistakes can require a …

{DistServe}: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving

Y Zhong, S Liu, J Chen, J Hu, Y Zhu, X Liu… - … USENIX Symposium on …, 2024 - usenix.org
DistServe improves the performance of large language models (LLMs) serving by
disaggregating the prefill and decoding computation. Existing LLM serving systems colocate …

CodeScholar: Growing Idiomatic Code Examples

M Shetty, K Sen, I Stoica - arXiv preprint arXiv:2312.15157, 2023 - arxiv.org
Programmers often search for usage examples for API methods. A tool that could generate
realistic, idiomatic, and contextual usage examples for one or more APIs would be …