PersonalAlign：面向个性化GUI代理的分层隐式意图对齐
PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records
AI总结：
本文提出PersonalAlign，通过长期用户记录实现个性化GUI代理的隐式意图对齐，引入AndroidIntent基准测试，评估代理在模糊指令解析和主动建议中的表现，HIM-Agent在执行和主动性能上提升显著。
摘要：
尽管GUI代理在显式和完成指令下表现优异，但实际部署需对用户复杂隐式意图进行对齐。本文提出面向个性化GUI代理的分层隐式意图对齐（PersonalAlign），要求代理利用长期用户记录作为持久上下文以解决模糊指令中的遗漏偏好，并通过用户状态预测潜在习惯以提供主动帮助。为促进此研究，我们引入AndroidIntent基准测试，评估代理在解析模糊指令和通过长期用户记录提供主动建议的能力。我们从20k长期记录中注释了775个用户特定偏好和215个习惯用于评估。此外，我们引入分层意图记忆代理（HIM-Agent），其维护持续更新的个人记忆并分层组织用户偏好和习惯以实现个性化。最后，我们在AndroidIntent上评估了多种GUI代理，包括GPT-5、Qwen3-VL和UI-TARS，进一步结果表明HIM-Agent在执行和主动性能上分别提升了15.7%和7.3%。
英文摘要：
While GUI agents have shown strong performance under explicit and completion instructions, real-world deployment requires aligning with users' more complex implicit intents. In this work, we highlight Hierarchical Implicit Intent Alignment for Personalized GUI Agent (PersonalAlign), a new agent task that requires agents to leverage long-term user records as persistent context to resolve omitted preferences in vague instructions and anticipate latent routines by user state for proactive assistance. To facilitate this study, we introduce AndroidIntent, a benchmark designed to evaluate agents' ability in resolving vague instructions and providing proactive suggestions through reasoning over long-term user records. We annotated 775 user-specific preferences and 215 routines from 20k long-term records across different users for evaluation. Furthermore, we introduce Hierarchical Intent Memory Agent (HIM-Agent), which maintains a continuously updating personal memory and hierarchically organizes user preferences and routines for personalization. Finally, we evaluate a range of GUI agents on AndroidIntent, including GPT-5, Qwen3-VL, and UI-TARS, further results show that HIM-Agent significantly improves both execution and proactive performance by 15.7% and 7.3%.
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。
