3 papers
cs.AI2025
Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition
Danielle Cohen, Yoni Halpern, Noam Kahlon +5
Understanding user intents from UI interaction trajectories remains a challenging, yet crucial, frontier in intelligent agent development. While massive, datacenter-based, multi-mo…
cs.HC2025
Agent-Initiated Interaction in Phone UI Automation
Noam Kahlon, Guy Rom, Anatoly Efros +6
Phone automation agents aim to autonomously perform a given natural-language user request, such as scheduling appointments or booking a hotel. While much research effort has been d…
cs.AI2025
Bi-Fact: A Bidirectional Factorization-based Evaluation of Intent Extraction from UI Trajectories
Sapir Caduri, Anatoly Efros, Noam Kahlon +3
Evaluating intent extraction from GUIs demands accurate, fine-grained metrics. This paper introduces Bi-Fact, a novel method that decomposes intents into atomic facts and performs…