On Automated Assistants for Software Development: The Role of LLMs
Authors:
Open Access
- 11 September 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1737-1741
Abstract
Software developers handle many complex tasks that include gathering and applying domain knowledge, coordinating subtasks, designing interfaces, turning ideas into elegant code, and more. They must switch contexts between these tasks, incurring more cognitive costs. Recent advances in large language models (LLMs) open up new possibilities for moving beyond the support provided by automated assistants (AAs) available today. In this paper, we explore if a human memory model can provide a framework for the systematic investigation of AAs for software development based on LLMs and other new technologies.Keywords
Funding Information
- NSERC (RGPIN-2022-03139)
This publication has 13 references indexed in Scilit:
- Transformers for GUI Testing: A Plausible Solution to Automated Test Case Generation and Flaky TestsComputer, 2022
- Latent Patterns in Activities: A Field Study of How Developers Manage Context2019
- ACT‐R: A cognitive architecture for modeling cognitionWIREs Cognitive Science, 2018
- Measuring neural efficiency of program comprehension2017
- Speculative analysis of integrated development environment recommendationsACM SIGPLAN Notices, 2012
- Reducing the effort of bug report triageACM Transactions on Software Engineering and Methodology, 2011
- Role-based refactoring of crosscutting concerns2005
- Modeling Working Memory in a Unified Architecture: An ACT-R Perspective1999
- The role of knowledge in software developmentCommunications of the ACM, 1999
- Program comprehension during software maintenance and evolutionComputer, 1995