arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.04747cs.SEcs.AI
收藏

每个软件皆可成为智能体:蓝图与案例研究

Every Software as an Agent: Blueprint and Case Study

Mengwei Xu

AI总结:

本文提出一种白盒软件智能体新范式,通过让大语言模型访问软件源代码与运行时上下文并动态注入生成代码,以提升智能体准确性与效率,并通过两个桌面应用案例验证其可行性。

摘要:

(多模态)大语言模型(LLMs)的兴起使软件智能体成为关注焦点——软件能够理解并遵循用户的自然语言指令。然而,现有方法(如基于 API 的智能体和基于 GUI 的智能体)在准确性和效率方面远不能令人满意。为此,我们主张赋予 LLMs 访问软件内部信息(源代码和运行时上下文)的权限,并允许其动态注入生成的代码到软件中执行。在这种白盒设置下,可以更好地利用软件上下文和 LLMs 的编码能力。随后,我们提出了整体设计架构,并在两个流行的基于 Web 的桌面应用程序上进行了案例研究。我们还深入讨论了面临的挑战和未来方向。我们认为,这种新范式有潜力从根本上颠覆现有的软件智能体设计,并最终创造一个数字世界,使软件能够理解、操作、协作甚至思考,以满足复杂的用户需求。

英文摘要:

The rise of (multimodal) large language models (LLMs) has shed light on software agent -- where software can understand and follow user instructions in natural language. However, existing approaches such as API-based and GUI-based agents are far from satisfactory at accuracy and efficiency aspects. Instead, we advocate to endow LLMs with access to the software internals (source code and runtime context) and the permission to dynamically inject generated code into software for execution. In such a whitebox setting, one may better leverage the software context and the coding ability of LLMs. We then present an overall design architecture and case studies on two popular web-based desktop applications. We also give in-depth discussion of the challenges and future directions. We deem that such a new paradigm has the potential to fundamentally overturn the existing software agent design, and finally creating a digital world in which software can comprehend, operate, collaborate, and even think to meet complex user needs.

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。

↑