AI for Software Engineering

Description

This research area explores the application of Artificial Intelligence (AI) techniques to Software Engineering, covering areas such as requirements engineering, software maintenance and evolution, software migration and modernization, and software testing

Team

Matías Martínez
UPC

Xavier Franch
UPC

Marc Oriol
UPC

Quim Motger
UPC

Lidia López
UPC

Silverio Martínez-Fernández
UPC

Carles Farré<
UPC

Outcomes/Main Contributions

Research:

Studying LLM-and Agentic based systems for program repair.
- What's in a Benchmark? The Case of SWE-Bench in Automated Program Repair. Matias Martinez, Xavier Franch. ICSE-SEIP 2026.

Teaching:

Teaching MLOps in Higher Education through Project-Based Learning:
- Experiences from Training Future Machine Learning Engineers with Software Engineering Practices.
- The state-of-the-art outcomes of this research area (and the sustainability of AI systems research area) are integrated into two subjects:
  - “Machine Learning Systems in Production” (MLOps) of the Master of Data Science at UPC.
  - “Advanced Topics of Data Engineering 2” (TAED2) of the Bachelor degree of Data Science and Engineering at UPC.

Community:

Involvement in SE&AI conferences:
- International Conference on AI Engineering – Software Engineering for AI (CAIN@ICSE).
- International Workshop on Software Architecture and Machine Learning (SAML).

Projects Overview

Title	Project Type	Goal
MLEvol (2025 - 2029)	Research	MLEvol's main goal is to develop Software Engineering (SE) methods, practices and tools to foster the continuous and efficient evolution of MLS and the subsequent adaptation of their MLOps life cycle considering the highly dynamic ML ecosystem.
HIVEMIND (2025-2027)	Research	HIVEMIND's main goal is to promote responsible software engineering practices that accelerate all stages of the software development lifecycle (SDLC), leveraging novel AI and data technologies.
DOGO4 ML (2021-2025)	Research	DOGO4ML proposes a holistic end-to-end framework to develop, operate and govern MLSS and their data. This framework revolves around the DevDataOps lifecycle, which unifies two software lifecycles: a DevOps lifecycle and a DataOps lifecycle.
AI4Software (2023-2025)	Research Network	Fostering collaboration between national research groups to enhance the application of AI methods within the software development lifecycle.

Collaborations

Contact

Matias Martinez
Contact Matias Martinez

Xavier Franch
Contact Xavier Franch