arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.04710cs.SEcs.AI
收藏

面向软件工程的 Morescient 生成式人工智能(扩展版)

Morescient GAI for Software Engineering (Extended Version)

University of Mannheim(曼海姆大学)

Marcus Kessel, Colin Atkinson

AI总结:

本文针对现有基于 LLM 的代码模型仅学习软件语法、语义可信度不足的问题,提出融合软件语义与静态信息的 Morescient GAI 愿景,并给出观测平台及开放科学路线图。

摘要:

生成式人工智能(GAI)技术自动检查、合成和修改软件工程工件的能力,有望彻底变革软件工程的各个方面。因此,将 GAI 用于软件工程任务,正成为软件工程研究中扩展最迅速的领域之一;自 2021 年以来,已有一百多种基于 LLM 的代码模型发布。然而,现有绝大多数代码模型都具有一个重大弱点——它们完全只在软件的语法层面上接受训练,这显著降低了它们在依赖软件语义的任务中的可信度。为解决这一问题,需要一类新型的“Morescient”GAI,使其能够“感知”软件的语义层面和静态层面(即在这两个层面上接受训练)。反过来,这又要求新一代软件观测平台能够以结构化且易于分析的方式生成大量执行观测结果。本文提出一个愿景与路线图,说明如何依据开放科学原则来工程化、演进并传播此类“Morescient”GAI 模型。

英文摘要:

The ability of Generative AI (GAI) technology to automatically check, synthesize and modify software engineering artifacts promises to revolutionize all aspects of software engineering. Using GAI for software engineering tasks is consequently one of the most rapidly expanding fields of software engineering research, with over a hundred LLM-based code models having been published since 2021. However, the overwhelming majority of existing code models share a major weakness - they are exclusively trained on the syntactic facet of software, significantly lowering their trustworthiness in tasks dependent on software semantics. To address this problem, a new class of "Morescient" GAI is needed that is "aware" of (i.e., trained on) both the semantic and static facets of software. This, in turn, will require a new generation of software observation platforms capable of generating large quantities of execution observations in a structured and readily analyzable way. In this paper, we present a vision and roadmap for how such "Morescient" GAI models can be engineered, evolved and disseminated according to the principles of open science.

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。

↑