State Your Intention to Steer Your Attention: An AI Assistant for Intentional Digital Living
Not on the map. Why?
Abstract (arXiv)
When working on digital devices, people often face distractions that can lead to a decline in productivity and efficiency, as well as negative psychological and emotional impacts. To address this challenge, we introduce a novel Artificial Intelligence (AI) assistant that elicits a user's intention, assesses whether ongoing activities are in line with that intention, and provides gentle nudges when deviations occur. The system leverages a large language model to analyze screenshots, application titles, and URLs, issuing notifications when behavior diverges from the stated goal. Its detection accuracy is refined through initial clarification dialogues and continuous user feedback. In a three-week, within-subjects field deployment with 22 participants, we compared our assistant to both a rule-based intent reminder system and a passive baseline that only logged activity. Results indicate that our AI assistant effectively supports users in maintaining focus and aligning their digital behavior with their intentions. Our source code is publicly available at https://intentassistant.github.io
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 25 of its 107 references that are in the map. First posted on arXiv 16 Oct 2025.
Builds on
25 of 107 references.
References · 25
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
- 2024WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMscited by 496
- 2024AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agentscited by 468
- 2024AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agentscited by 437
- 2024ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterizationcited by 61
- 2024Benchmarking Mobile Device Control Agents across Diverse Configurationscited by 55
- 2024MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Controlcited by 51
- 2023MindfulDiary: Harnessing Large Language Model to Support Psychiatric Patients' Journalingcited by 50
- 2025Creating General User Models from Computer Usecited by 44
- 2024Need Help? Designing Proactive AI Assistants for Programmingcited by 43
13 more
- 2024CLEAR: Towards Contextual LLM-Empowered Privacy Policy Analysis and Risk Generation for Large Language Model Applicationscited by 33
- 2024GPTCoach: Towards LLM-Based Physical Activity Coachingcited by 29
- 2023Enabling On-Device Large Language Model Personalization with Self-Supervised Data Selection and Synthesiscited by 20
- 2020'I Just Want to Hack Myself to Not Get Distracted': Evaluating Design Interventions for Self-Control on Facebookcited by 17
- 2023MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Interventioncited by 16
- 2021How the Design of YouTube Influences User Sense of Agencycited by 12
- 2019Self-Control in Cyberspace: Applying Dual Systems Theory to a Review of Digital Self-Control Toolscited by 8
- 2025sudo rm -rf agentic_securitycited by 8
- 2025Mirai: A Wearable Proactive AI "Inner-Voice" for Contextual Nudgingcited by 6
- 2024Time2Stop: Adaptive and Explainable Human-AI Loop for Smartphone Overuse Interventioncited by 5
- 2021Not Now, Ask Later: Users Weaken Their Behavior Change Regimen Over Time, But Expect To Re-Strengthen It Imminentlycited by 4
- 2025Empathetic Conversational Agents: Utilizing Neural and Physiological Signals for Enhanced Empathetic Interactionscited by 3
- 2016Productive, Anxious, Lonely - 24 Hours Without Push Notificationscited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.