Rethinking Software Engineering in the Era of Foundation Models: A Curated Catalogue of Challenges in the Development of Trustworthy FMware
Authors:
- Ahmed E. HassanAHAhmed E. Hassan
- Jiahuei LinJLJiahuei Lin
- Zhen Ming JiangZJZhen Ming Jiang
Preprint
Abstract
Foundation models (FMs), such as Large Language Models (LLMs), have revolutionized software development by enabling new use cases and business models. We refer to software built using FMs as FMware. The unique properties of FMware (e.g., prompts, agents, and the need for orchestration), coupled with the intrinsic limitations of FMs (e.g., hallucination) lead to a completely new set of software engineering challenges. Based on our industrial experience, we identified 10 key SE4FMware challenges that have caused enterprise FMware development to be unproductive, costly, and risky. In this paper, we discuss these challenges in detail and state the path for innovation that we envision. Next, we present FMArts, which is our long-term effort towards creating a cradle-to-grave platform for the engineering of trustworthy FMware. Finally, we (i) show how the unique properties of FMArts enabled us to design and develop a complex FMware for a large customer in a timely manner and (ii) discuss the lessons that we learned in doing so. We hope that the disclosure of the aforementioned challenges and our associated efforts to tackle them will not only raise awareness but also promote deeper and further discussions, knowledge sharing, and innovative solutions across the software engineering discipline.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Generative Artificial Intelligence for Software Engineering—A Research AgendaSoftware: Practice and Experience, 2025
- Prompt Sapper: A LLM-Empowered Production Tool for Building AI ChainsACM Transactions on Software Engineering and Methodology, 2024
- A Comprehensive Survey of Continual Learning: Theory, Method and ApplicationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- Lost in the Middle: How Language Models Use Long ContextsTransactions of the Association for Computational Linguistics, 2024
- Taking AI risks seriously: a new assessment model for the AI ActAI & SOCIETY, 2023
- Survey of Hallucination in Natural Language GenerationACM Computing Surveys, 2023
- Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language ProcessingACM Computing Surveys, 2023
- Instruction Induction: From Few Examples to Natural Language Task Descriptions2023
- Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation With Large Language ModelsIEEE Transactions on Visualization and Computer Graphics, 2022
- Software Engineering for Machine Learning: A Case Study2019