AI 中文总结
本研究通过推出编码智能体Ark及基准ArkBench，探索了编码智能体的架构，用gpt-5.4-mini测试Ark解决10项任务中的8项，还对比了其与先进编码智能体的架构，为相关研究提供基础。
AI 中文摘要
编码智能体已迅速成为AI辅助软件开发的主要界面。然而，尽管它们的应用日益广泛，人们对其内部架构却知之甚少，目前也不存在可与编译器或操作系统相媲美的系统性架构描述。本文通过记录编码智能体的主要架构组件，解释其职责、交互及执行流程，以填补这一空白。为支持此项工作，我们还推出了Ark（Agent Research Kit），这是一款极简开源编码智能体，专为研究和教育设计，既保留了现代编码智能体的核心架构机制，又强调简洁性与清晰性。此外，我们还推出了ArkBench，这是一个包含10项代表性软件维护与演化任务的轻量级基准。使用gpt-5.4-mini时，Ark成功解决了10项任务中的8项，且仅需适度的token消耗。最后，我们采用最新提出的架构分类法，将Ark的架构与最先进编码智能体的架构进行了对比。我们希望Ark和ArkBench能为编码智能体的教学、研究及实验提供实用基础。
英文摘要
Coding agents have rapidly emerged as the primary interface for AI-assisted software development. However, despite their growing adoption, relatively little is known about their internal architecture, and no systematic architectural description comparable to those available for compilers or operating systems currently exists. This paper addresses this gap by documenting the main architectural components of coding agents, explaining their responsibilities, interactions, and execution flow. To support this effort, we also present Ark (Agent Research Kit), a minimal open-source coding agent designed for research and education that preserves the essential architectural mechanisms of modern coding agents while emphasizing simplicity and clarity. We also introduce ArkBench, a lightweight benchmark comprising ten representative software maintenance and evolution tasks. Using gpt-5.4-mini, Ark successfully solved 8 of the 10 tasks while requiring modest token consumption. Finally, we compare the architecture of Ark with those of state-of-the-art coding agents using a recently proposed architectural taxonomy. We hope that both Ark and ArkBench provide a practical foundation for teaching, research, and experimentation on coding agents.
