让GUI助手理解用户长期习惯，主动预判需求。
PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records
- 分层记忆机制存储用户偏好与行为模式
- 在模糊指令下执行准确操作，主动建议提升7.3%
- 适合需要个性化长期服务的智能助手场景
尽管GUI代理在明确指令下表现良好，但真实场景中需应对复杂的隐式意图。本文提出个人化GUI代理的层级隐式意图对齐任务（PersonalAlign），要求代理利用长期用户记录作为持续上下文，补全模糊指令中的省略偏好，并基于用户状态预测潜在操作流程以提供主动帮助。为此，我们构建了AndroidIntent基准，从2万条跨用户长期记录中标注了775个个性化偏好和215个行为模式用于评估。同时提出分层意图记忆代理（HIM-Agent），通过持续更新的个人记忆，分层组织用户偏好与习惯。在GPT-5、Qwen3-VL和UI-TARS等模型上评估发现，HIM-Agent使执行成功率提升15.7%，主动建议能力提升7.3%。
原文摘要 · Abstract (English)
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%.
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。