OpenPhone proposes a device-cloud collaboration system for mobile GUI agents, pairing an enhanced 3B on-device model with cloud models to balance cost and capability. The approach uses two-stage SFT then GRPO training on…

#OpenSourceAI #MobileAI #GUIAgents #MLLM
https://arxiv.org/abs/2510.22009

A new system called PastForward speeds up on-device GUI agents by reusing fine-grained computational experience from prior tasks as multi-token proposals, reducing the need for full vision-language model inference at every step…

#EdgeAI #GUIagents #OnDeviceAI #VLM
https://arxiv.org/abs/2609.32166

VLAA-GUI is a modular framework for GUI automation that tackles early stopping and repetitive loops via a Completeness Verifier and a Loop Breaker component, requiring direct visual evidence before declaring success. The…

#VLAA #GUIAgents #Robotics #Automation
https://arxiv.org/abs/2604.21375

New arXiv paper introduces GUI-Hopper, which augments mobile GUI agents with app-native deeplinks discovered through static analysis and validated on real devices. The hybrid approach replaces multi-step tap sequences with single…

#AI #MobileAI #GUIagents #HCI
https://arxiv.org/abs/2609.30887