重思基础模型时代的软件工程:可信 FMware 开发挑战精选目录
Rethinking Software Engineering in the Foundation Model Era: A Curated Catalogue of Challenges in the Development of Trustworthy FMware
AI总结:
本文梳理企业级可信 FMware 开发中的 10 个 SE4FMware 关键挑战,并提出覆盖全生命周期的 FMArts 平台,结合大型客户复杂系统实践验证其工程价值。
摘要:
基础模型(FMs),例如大语言模型(LLMs),已经通过催生新的用例和商业模式而彻底改变了软件开发。我们将使用 FMs 构建的软件称为 FMware。FMware 的独特属性(例如提示词、智能体以及编排需求),加上 FMs 的内在局限(例如幻觉),带来了一系列全新的软件工程挑战。基于我们的工业经验,我们识别出 10 个关键的 SE4FMware 挑战,这些挑战已导致企业级 FMware 开发低效、昂贵且充满风险。在本文中,我们详细讨论这些挑战,并阐述我们所设想的创新路径。随后,我们介绍 FMArts,这是我们为创建可信 FMware 工程的从摇篮到坟墓平台而开展的长期工作。最后,我们(i)展示 FMArts 的独特属性如何使我们能够及时为一家大型客户设计并开发复杂的 FMware,以及(ii)讨论我们在此过程中获得的经验教训。我们希望,披露上述挑战以及我们为应对这些挑战所做的相关努力,不仅能够提高认识,还能在整个软件工程学科中促进更深入、更长远的讨论、知识共享和创新解决方案。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。