PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records

TL;DR

H Hierarchical Implicit Intent Alignment for Personalized GUI Agent (PersonalAlign) is highlighted, 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.

Abstract

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%.

Figures (7)

• Figure 1: We highlight a new PersonalAlign agent task. Agent should leverage the user’s long-term record to provide hierarchical implicit intent alignment for both preference and routine intent.
• Figure 2: Overview of AndroidIntent collection pipeline. We employ a two-stage filtering-verification, integrating objective criteria with subjective judgment to hierarchically annotate user intent from long-horizon records.
• Figure 3: Visualization of the user's intents distribution by aggregating all executing records across users. At a sufficient scale, the intent statistics exhibit three approximately Gaussian-like distributions.
• Figure 4: Overview of HIM-Agent. The Streaming Aggregation Module updates user records daily, and the aggregated prototypes are hierarchically organized to support personalized preference and routine intent.
• Figure 5: Ablation study of components for proactive performance. Lower of False-Alarm means better align.