arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.03798cs.SEcs.CLcs.CV
收藏

全栈代理:通过面向开发的测试和仓库反翻译增强全栈网页编码

FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation

Multimedia Laboratory (MMLab), The Chinese University of Hong Kong(香港中文大学多媒体实验室);Shenzhen Loop Area Institute(深圳河套学院)

Zimu Lu, Houxing Ren, Yunqiao Yang, Ke Wang, Zhuofan Zong, Mingjie Zhan, Hongsheng Li

AI总结:

FullStack-Agent通过面向开发的测试和仓库反翻译提升全栈网页编码能力,其多代理框架和自我改进方法在多个测试用例中表现出色。

摘要:

帮助非专家用户开发复杂的交互式网站已成为LLM驱动的代码代理的热门任务。然而,现有代码代理往往只生成前端网页,用炫酷的视觉效果掩盖了缺乏真实全栈数据处理和存储的缺陷。值得注意的是,构建生产级别的全栈网页应用比仅生成前端网页更具挑战性,需要精心控制数据流,全面理解不断更新的包和依赖关系,并准确定位代码库中的隐晦错误。为了解决这些困难,我们引入了FullStack-Agent,一个统一的全栈代理系统,由三个部分组成:(1)FullStack-Dev,一个多代理框架,具有强大的规划、代码编辑、代码库导航和错误定位能力。(2)FullStack-Learn,一种创新的数据扩展和自我改进方法,通过反向翻译爬取和合成的网站仓库来提高FullStack-Dev的主干LLM。(3)FullStack-Bench,一个全面的基准测试,系统地测试生成网站的前端、后端和数据库功能。我们的FullStack-Dev在前端、后端和数据库测试用例上分别优于先前的最先进方法8.7%、38.2%和15.9%。此外,FullStack-Learn通过自我改进将30B模型的性能提高了9.7%、9.5%和2.8%,证明了我们方法的有效性。代码已发布在https://github.com/mnluzimu/FullStack-Agent。

英文摘要:

Assisting non-expert users to develop complex interactive websites has become a popular task for LLM-powered code agents. However, existing code agents tend to only generate frontend web pages, masking the lack of real full-stack data processing and storage with fancy visual effects. Notably, constructing production-level full-stack web applications is far more challenging than only generating frontend web pages, demanding careful control of data flow, comprehensive understanding of constantly updating packages and dependencies, and accurate localization of obscure bugs in the codebase. To address these difficulties, we introduce FullStack-Agent, a unified agent system for full-stack agentic coding that consists of three parts: (1) FullStack-Dev, a multi-agent framework with strong planning, code editing, codebase navigation, and bug localization abilities. (2) FullStack-Learn, an innovative data-scaling and self-improving method that back-translates crawled and synthesized website repositories to improve the backbone LLM of FullStack-Dev. (3) FullStack-Bench, a comprehensive benchmark that systematically tests the frontend, backend and database functionalities of the generated website. Our FullStack-Dev outperforms the previous state-of-the-art method by 8.7%, 38.2%, and 15.9% on the frontend, backend, and database test cases respectively. Additionally, FullStack-Learn raises the performance of a 30B model by 9.7%, 9.5%, and 2.8% on the three sets of test cases through self-improvement, demonstrating the effectiveness of our approach. The code is released at https://github.com/mnluzimu/FullStack-Agent.

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。

↑