用精炼知识替代频繁调用大模型，让手机应用探索更高效省钱。
LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps
- 只在维护知识时调用大模型，其余步骤无需大模型生成动作。
- 在20个典型应用上实现最高覆盖率和最快探索速度，成本低148倍。
- 适合需要低成本自动化测试的移动开发与安全团队使用。
大语言模型（LLM）为自动化移动应用探索带来了新机遇，解决了过去难以生成有意义用户界面交互的难题。然而，现有基于LLM的探索方法几乎每一步都依赖大模型生成动作，导致高昂的令牌费用和计算资源消耗。本文认为这种大规模使用大模型既不必要也不高效，因为探索过程中的许多操作并不需要或甚至会受大模型能力干扰。基于“精确而紧凑的知识对有效探索至关重要”的洞察，我们提出 LLM-Explorer，一种专为高效与低成本设计的新探索代理。该方法主要利用大模型维护知识，而动作生成则在无大模型参与下完成。在20个典型应用上与5个强基线对比，LLM-Explorer实现了最快的探索速度和最高的覆盖率，成本比当前最先进的基于大模型的方法降低超过148倍。
原文摘要 · Abstract (English)
Large language models (LLMs) have opened new opportunities for automated mobile app exploration, an important and challenging problem that used to suffer from the difficulty of generating meaningful UI interactions. However, existing LLM-based exploration approaches rely heavily on LLMs to generate actions in almost every step, leading to a huge cost of token fees and computational resources. We argue that such extensive usage of LLMs is neither necessary nor effective, since many actions during exploration do not require, or may even be biased by the abilities of LLMs. Further, based on the insight that a precise and compact knowledge plays the central role for effective exploration, we introduce LLM-Explorer, a new exploration agent designed for efficiency and affordability. LLM-Explorer uses LLMs primarily for maintaining the knowledge instead of generating actions, and knowledge is used to guide action generation in a LLM-less manner. Based on a comparison with 5 strong baselines on 20 typical apps, LLM-Explorer was able to achieve the fastest and highest coverage among all automated app explorers, with over 148x lower cost than the state-of-the-art LLM-based approach.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。