# Curiosity Driven Knowledge Retrieval for Mobile Agents

arXiv: https://arxiv.org/abs/2601.19306 · HTML: https://mlsanity.com/paper/2601.19306/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 82 references that are in the map.
- First posted on arXiv 27 Jan 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, 17 of 17)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents](https://mlsanity.com/paper/2401.10935/) (2024)
- [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024)
- [Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents](https://mlsanity.com/paper/2504.00906/) (2025)
- [Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning](https://mlsanity.com/paper/2405.10292/) (2024)
- [Aria-UI: Visual Grounding for GUI Instructions](https://mlsanity.com/paper/2412.16256/) (2024)
- [Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment](https://mlsanity.com/paper/2503.15937/) (2025)
- [GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent](https://mlsanity.com/paper/2505.16827/) (2025)
- [CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models](https://mlsanity.com/paper/2509.09675/) (2025)
- [Curiosity-Driven Exploration via Latent Bayesian Surprise](https://mlsanity.com/paper/2104.07495/) (2021)
- [Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detection](https://mlsanity.com/paper/2409.09953/) (2024)
- [WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making](https://mlsanity.com/paper/2506.06725/) (2025)
- [SymAgent: A Neural-Symbolic Self-Learning Agent Framework for Complex Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2502.03283/) (2025)
- [AndroidGen: Building an Android Language Agent under Data Scarcity](https://mlsanity.com/paper/2504.19298/) (2025)
- [Curiosity-Driven Testing for Sequential Decision-Making Process](https://mlsanity.com/paper/2509.02025/) (2025)

## Built on by (most cited first, 1 of 1)

- [Not an A11y: How Android Accessibility Exposes Mobile AI Agents to Indirect Prompt Injection](https://mlsanity.com/paper/2608.08939/) (2026)

## Abstract (arXiv)

Mobile agents have made progress toward reliable smartphone automation, yet performance in complex applications remains limited by incomplete knowledge and weak generalization to unseen environments. We introduce a curiosity driven knowledge retrieval framework that formalizes uncertainty during execution as a curiosity score. When this score exceeds a threshold, the system retrieves external information from documentation, code repositories, and historical trajectories. Retrieved content is organized into structured AppCards, which encode functional semantics, parameter conventions, interface mappings, and interaction patterns. During execution, an enhanced agent selectively integrates relevant AppCards into its reasoning process, thereby compensating for knowledge blind spots and improving planning reliability. Evaluation on the AndroidWorld benchmark shows consistent improvements across backbones, with an average gain of six percentage points and a new state of the art success rate of 88.8% when combined with GPT-5. Analysis indicates that AppCards are particularly effective for multi step and cross application tasks, while improvements depend on the backbone model. Case studies further confirm that AppCards reduce ambiguity, shorten exploration, and support stable execution trajectories. Task trajectories are publicly available at https://lisalsj.github.io/Droidrun-appcard/.