Collaborative agents for software engineering
Code review is a heavily collaborative process, which aims at ensuring the overall quality
and reliability of software. While it provides massive benefits, the implementation of code …
and reliability of software. While it provides massive benefits, the implementation of code …
Advanced large language models and visualization tools for data analytics learning
J Valverde-Rebaza, A González… - Frontiers in …, 2024 - frontiersin.org
Introduction In recent years, numerous AI tools have been employed to equip learners with
diverse technical skills such as coding, data analysis, and other competencies related to …
diverse technical skills such as coding, data analysis, and other competencies related to …
Bridging design and development with automated declarative ui code generation
Declarative UI frameworks have gained widespread adoption in mobile app development,
offering benefits such as improved code readability and easier maintenance. Despite these …
offering benefits such as improved code readability and easier maintenance. Despite these …
CodeAgent: Autonomous Communicative Agents for Code Review
Code review, which aims at ensuring the overall quality and reliability of software, is a
cornerstone of software development. Unfortunately, while crucial, Code review is a labor …
cornerstone of software development. Unfortunately, while crucial, Code review is a labor …
Swe-bench+: Enhanced coding benchmark for llms
Large Language Models (LLMs) in Software Engineering (SE) can offer assistance for
coding. To facilitate a rigorous evaluation of LLMs in practical coding contexts, Carlos et al …
coding. To facilitate a rigorous evaluation of LLMs in practical coding contexts, Carlos et al …
GPT-4 as a homework tutor can improve student engagement and learning outcomes
This work contributes to the scarce empirical literature on LLM-based interactive homework
in real-world educational settings and offers a practical, scalable solution for improving …
in real-world educational settings and offers a practical, scalable solution for improving …
You Don't Have to Say Where to Edit! jLED–Joint Learning to Localize and Edit Source Code
Learning to edit code automatically is becoming more and more feasible. Thanks to recent
advances in Neural Machine Translation (NMT), various case studies are being investigated …
advances in Neural Machine Translation (NMT), various case studies are being investigated …
When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair
Software systems have been evolving rapidly and inevitably introducing bugs at an
increasing rate, leading to significant losses in resources consumed by software …
increasing rate, leading to significant losses in resources consumed by software …
Detecting Multi-Parameter Constraint Inconsistencies in Python Data Science Libraries
Modern AI-and Data-intensive software systems rely heavily on data science and machine
learning libraries that provide essential algorithmic implementations and computational …
learning libraries that provide essential algorithmic implementations and computational …
Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repair
Q Feng, X Ma, J Sheng, Z Feng, W Song… - arxiv preprint arxiv …, 2024 - arxiv.org
LLMs have garnered considerable attention for their potential to streamline Automated
Program Repair (APR). LLM-based approaches can either insert the correct code or directly …
Program Repair (APR). LLM-based approaches can either insert the correct code or directly …