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 in software engineering.
Deep learning and LLMs for software reuse, evolution, and maintenance tasks.
LLM-based code and documentation generation from natural language specifications.
AI-driven software prototyping, defect prediction, and refactoring.
Generative and retrieval-augmented models for knowledge discovery in repositories, forums, and documentation.
Data augmentation using generative networks.
AI-assisted software development and pair programming.
Agent-based iterative and incremental processes for adaptive planning, coordination, and continuous feedback.
Explainable and trustworthy AI in SE: governance, ethics, and human-in-the-loop methodologies.
Mining software repositories, reverse engineering, and program comprehension.
Semantic reasoning, ontologies, and knowledge-based systems for software analysis and design.
Business process management and automation through AI.
Cost analysis, risk assessment, and technical debt prediction.
Model-driven development and domain modeling.
Software modeling techniques supporting explainable AI.
AI-enhanced educational tools and learning analytics for SE education and training.
Evaluation frameworks and metrics for AI-based SE tools and processes.
AI for emerging paradigms: big data, cloud computing, IoT, and hybrid/quantum AI.
AI-powered search engines and intelligent information retrieval in SE.
Case studies and real-world applications of AI technologies in software engineering.
Establishing standards and benchmarks for AI in SE.