A Tutorial on Software Engineering for FMware
Foundation Models (FMs) like GPT-4 have given rise to FMware, FM-powered applications representing a new generation of software that is developed under new paradigms. FMware has been widely adopted in both software engineering (SE) research (e.g., test generation) and industrial products (e.g., GitHub copilot), despite the numerous challenges introduced by the stochastic nature of FMs. In our tutorial, we will present the latest research and industry practices in engineering FMware. Our tutorial's perspective is firmly rooted in SE rather than artificial intelligence (AI), ensuring its accessibility to FSE participants.
Authors
- Jiahuei Lin (ORCID: https://orcid.org/0000-0002-7133-2219)
- Filipe R. Cogo (ORCID: https://orcid.org/0000-0002-5494-685X)
- Gopi Krishnan Rajbahadur (ORCID: https://orcid.org/0000-0003-1812-5365)
- Gustavo A. Oliva (ORCID: https://orcid.org/0000-0002-5419-9284)
- Dayi Lin (ORCID: https://orcid.org/0000-0002-4034-6650)
- Keheliya Gallaba (ORCID: https://orcid.org/0000-0002-5880-5114)
- Ahmed E. Hassan (ORCID: https://orcid.org/0000-0001-7749-5513)
- Benjamin Rombaut (ORCID: https://orcid.org/0000-0001-5947-2684)
- Kirill Vasilevski
Institutions
- Queen's University (CA)
- Huawei Technologies (Canada) (CA)
Publication Details
- Published
- 2025-06-23
- DOI
- https://doi.org/10.1145/3696630.3728621
- Primary Topic
- Manufacturing Process and Optimization
- Type
- article
- Field-Weighted Citation Impact
- 0.00