arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.09540cs.SE
收藏

SWE-Bench Mobile: 大语言模型代理能否开发行业级移动应用?

SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications?

University of Toronto(多伦多大学);Xiaohongshu Inc.(小红书);Coolwei AI Lab(酷维人工智能实验室);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of California, Berkeley(加利福尼亚大学伯克利分校)

Muxin Tian, Zhe Wang, Blair Yang, Zhenwei Tang, Kunlun Zhu, Honghua Dong, Hanchen Li, Xinni Xie, Guangjing Wang, Jiaxuan You

AI总结:

SWE-Bench Mobile评估大语言模型代理在开发行业级移动应用中的能力,发现商业代理表现优于开源替代品,且简单提示策略更有效。

摘要:

大语言模型代理能否开发行业级移动应用?我们介绍了SWE-Bench Mobile,这是一个用于评估编码代理在现实软件工程任务上的基准,这些任务来源于一个生产级的iOS代码库。与现有仅关注孤立问题或bug修复的基准不同,SWE-Bench Mobile捕捉到了工业开发的全部复杂性:多模态输入(PRD和Figma设计)、大规模的混合Swift/Objective-C代码库以及全面的测试套件。我们评估了22种代理-模型配置,涵盖四个编码代理——三个商业(Cursor、Codex、Claude Code)和一个开源(OpenCode)——发现即使最佳配置也只能达到12%的任务成功率。我们的分析揭示了(1)代理设计与模型能力同样重要——相同模型在不同代理上表现存在高达6倍的性能差距;(2)商业代理始终优于开源替代品;(3)简单的『防御性编程』提示比复杂提示高出7.4%。这些发现突显了当前代理能力与工业需求之间显著的差距,同时为从业者和研究人员提供了可操作的见解。我们发布SWE-Bench Mobile作为一项『托管基准挑战』以防止数据污染并确保公平评估。公共排行榜和开发工具包可在https://swebenchmobile.com上获得。

英文摘要:

Can large language model agents develop industry-level mobile applications? We introduce \textbf{SWE-Bench Mobile}, a benchmark for evaluating coding agents on realistic software engineering tasks derived from a production iOS codebase. Unlike existing benchmarks that focus on isolated problems or bug fixes, SWE-Bench Mobile captures the full complexity of industrial development: multi-modal inputs (PRDs and Figma designs), a large-scale mixed Swift/Objective-C codebase, and comprehensive test suites. We evaluate 22 agent-model configurations across four coding agents -- three commercial (Cursor, Codex, Claude Code) and one open-source (OpenCode) -- and find that even the best configurations achieve only 12\% task success rate. Our analysis reveals that (1) agent design matters as much as model capability -- the same model shows up to 6$\times$ performance gap across agents, (2) commercial agents consistently outperform open-source alternatives, and (3) simple ``Defensive Programming'' prompts outperform complex ones by 7.4\%. These findings highlight a significant gap between current agent capabilities and industrial requirements, while providing actionable insights for practitioners and researchers. We release SWE-Bench Mobile as a \textit{hosted benchmark challenge} to prevent data contamination and ensure fair evaluation. The public leaderboard and development toolkit are available at https://swebenchmobile.com.

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。

↑