# Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents

arXiv: https://arxiv.org/abs/2609.33304 · HTML: https://mlsanity.com/paper/2609.33304/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 24 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 20 of 20)

- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation](https://mlsanity.com/paper/2604.08455/) (2026)
- [FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents](https://mlsanity.com/paper/2507.21071/) (2025)
- [PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records](https://mlsanity.com/paper/2601.09636/) (2026)
- [Evaluating Long-Context Reasoning in LLM-Based WebAgents](https://mlsanity.com/paper/2512.04307/) (2025)
- [Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants](https://mlsanity.com/paper/2604.00842/) (2026)
- [Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History](https://mlsanity.com/paper/2602.17003/) (2026)
- [Hybrid Self-evolving Structured Memory for GUI Agents](https://mlsanity.com/paper/2603.10291/) (2026)
- [MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents](https://mlsanity.com/paper/2605.18652/) (2026)
- [WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces](https://mlsanity.com/paper/2606.09426/) (2026)
- [Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs](https://mlsanity.com/paper/2510.00507/) (2025)
- [ColorAgent: Building A Robust, Personalized, and Interactive OS Agent](https://mlsanity.com/paper/2510.19386/) (2025)
- [Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction](https://mlsanity.com/paper/2601.20162/) (2026)
- [PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents](https://mlsanity.com/paper/2603.08013/) (2026)
- [MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents](https://mlsanity.com/paper/2606.16748/) (2026)
- [ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices](https://mlsanity.com/paper/2602.21858/) (2026)
- [PSPA-Bench: A Personalized Benchmark for Smartphone GUI Agent](https://mlsanity.com/paper/2603.29318/) (2026)
- [Executable Agentic Memory for GUI Agent](https://mlsanity.com/paper/2605.12294/) (2026)
- [What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States](https://mlsanity.com/paper/2606.31612/) (2026)
- [Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization](https://mlsanity.com/paper/2604.11259/) (2026)

## Abstract (arXiv)

Personal Graphical User Interface (GUI) agents rely on interaction history to infer what a user wants from ambiguous instructions and to anticipate recurring routines. Existing approaches retrieve task-relevant history and append it to the policy's context, implicitly assuming that experience relevant to a task remains useful for each decision within it. We find that this help is largely spent at the first decision: retrieved history strongly improves the opening step of an episode, yet provides little sustained benefit over the remaining 90% of steps, and offers weak guidance on whether a proactive suggestion is warranted. A relevant record may tell the agent where to begin, but not which past action applies to the current screen or whether a routine is due now. The underlying issue is that relevance does not imply applicability: relevance is determined at the task level, whereas applicability depends on the situation at decision time. We therefore recast personalization as experience activation and introduce ExpActivator, a training-free framework that activates only the experience applicable to the current situation. During execution, ExpActivator matches each new screen to historical states in the frozen GUI backbone's latent space and supplies the corresponding action as a reference. Before execution, it activates a recurring intent only when the current time and scenario provide sufficient support, and otherwise abstains. Across four GUI backbones, ExpActivator improves within-trajectory step success by 28% on average, achieves the best personalized execution on every backbone while using about one-fifth as many history tokens, and reaches approximately 2.3× the Matthews correlation coefficient of the strongest proactive baseline. Experience pays where it is activated, not where it is appended.