Call for Papers

The goal of this special session is to leverage the strengths of deep learning,  and LLMs in particular, to address the unique challenges in software engineering, improving research outcomes, teaching methodologies, and industrial practices.

Topics of interest include but are not limited to:

• AI techniques for optimization, transformation, and configuration management focusing on how AI can enhance these critical aspects of software engineering.

• Applying deep learning and LLMs to software reuse, evolution and maintenance tasks.

• Using LLMs to generate software prototypes based on specifications provided in natural language, enabling a faster development cycle.

• Create LLM-based models to search for solutions to specific problems in forums, online documentation, and other resources.

• Data augmentation based on the use of generative networks.

• AI-driven approaches for mining software repositories and categorization.
  Reverse engineering and program comprehension fostering approaches to improve understanding of software for system deeper insights.

• Code search, querying and summarizing, in particular using LLMs

• Code generation, bug localization, fixing and patch generation, in particular using LLMs

• AI-assisted software development and AI-driven pair programming

• Concurrent/parallel software development and maintenance

• Semantic aspects in software engineering, including ontology and semantic reasoning for improved software projects understanding and management.

• Business process management and business rules automation for software engineering tasks

• Cost analysis, risk assessment, and technical debt assessment in software projects

• Model-driven development and domain modeling

• Software modeling techniques for explainable AI 

• Software tools that combine AI technologies with software engineering practices and tools to build AI-based software systems.

• Studies showing the implications and potential applications of quantum AI in software engineering.

• Showcasing real-world examples of AI applications in the software engineering industry.

• establishing standards and benchmarks for evaluating AI in software engineering.

• Agent-based software engineering.

• Formal methods in AI techniques for the development of reliable AI systems.

• AI for emerging paradigms and systems including big data, cloud computing, and IOT in the context of AI and software engineering

• Software for knowledge acquisition and representation to discuss software solutions for capturing and representing knowledge in AI systems.

• Software metrics applied to AI techniques to evaluate and improve AI methodologies in software engineering.

• Intelligent search engines in SE and AI-powered search engines for efficient information retrieval specific to software engineering.