Get Started
Home
Topics
Search
Library
Research questionHow can mobile GUI agents reliably interpret older adults’ indirect, ambiguous, and underspecified smartphone requests?Older adults may describe smartphone tasks indirectly, ambiguously, or without enough detail for an agent to identify the intended action. Benchmarks built around explicit goal-oriented instructions can therefore overestimate how reliably agents operate in realistic interactions.
AI
AI Agents
Computer Vision
Evaluation & Benchmarks
Multimodal Models
Natural Language Processing
Latest papersRecent research connected to this question, newest first.ElderBench: Benchmarking Autonomous Mobile Agents for Older AdultsThe evidence concerns smartphone GUI agents evaluated on 249 naturally elicited tasks from older adults across 20 applications, using online and offline settings. It includes comparisons with existing benchmark language, evaluations of mainstream GUI agents and vision-language models, instruction normalization, failure analysis, and fine-grained analysis of elderly-specific linguistic features.research paper · Sep 4, 2026
Related questions
How can in-car LLM agents respond consistently to incomplete requests they cannot safely fulfill?How can GUI agents preserve task success while reducing context, computation, action, and runtime costs?How can mobile agents execute tasks through direct, clearly bounded device capabilities instead of long GUI sequences?How can mobile GUI agents assess proposed actions before execution to avoid irreversible harm?