Workshop on GenAI Based Software Engineering

Objective of Workshop

The Software Development Life Cycle (SDLC) governs the creation of software systems, encompassing various engineering phases such as requirement specification, design, coding, testing, and maintenance. Software development is an effort-intensive and time-consuming activity whereas systems today need to reflect changes as quickly as possible. Most complex, large-scale software systems of today derive their requirements from existing (legacy) software and partial (incomplete) descriptions. Software development is thus a complex combination of transformation, reverse and forward engineering, involving code, data, and specifications, where data is both structured and unstructured. Expertise from subject matter specialists (SMEs) is essential at each phase, which brings in the important component of knowledge. While Model-Driven Engineering (MDE), Knowledge Engineering (KE), and Reverse Engineering (RE) have mitigated some of the challenges, the emergence of Generative AI techniques holds the potential for a substantial breakthrough. These techniques empower SMEs to construct purposeful engineering artifacts using natural language interactions.

The proposed workshop aims to provide a collaborative platform for researchers and practitioners to delve into the convergence of traditional MDE, KE, and RE methodologies together with Generative AI technologies. By synergizing the strengths of Gen AI, modeling, and knowledge representation for SDLC, our goal is to define a trajectory toward enhanced software engineering practices. We seek discussion on the following pivotal questions:

1. The development of industry-strength software is a multi-skill, long-drawn activity that cannot be effectively addressed by LLMs alone. What’s the right augmentation required?
2. LLM is a vast storehouse of general information, but the typical need during software development is rather sharply focused. How best to bear local knowledge to get the required focus?
3. Should one have to go to LLM every time and be vulnerable to its limitations?
4. Is fine-tuning LLM the only way, or purposive knowledge representation can perform far better at times?
5. Can Generative AI play a role in constructing purpose-driven knowledge representations?
6. How can Generative AI enhance the program analysis-driven techniques for understanding programs and extracting knowledge?
7. How does Generative AI outshine other natural language processing techniques in software engineering contexts?
8. How can Generative AI enhance the synthesis of tests and test data for a given set of requirements, and given code?
9. Can problem fixes and change requests be analyzed and implemented expeditiously using Generative AI?

The workshop aims to foster interactive discussions, enabling participants to collectively shape the future of advanced software engineering. The inaugural edition will feature talks by invited speakers who are exploring one or more of the above questions, interspersed with short experiences of researchers who are exploring specific challenges of software engineering using GenAI techniques. Time permitting, we will have short lightening talks by researchers to share interesting observations and anecdotes.