Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents
For developers of proactive mobile agents, PRPF addresses the goal misalignment and redundant inference in existing MLLM-based systems by decoupling intervention and reasoning.
PRPF introduces a two-stage framework that separates intervention gating from reasoning, using a lightweight perceptor to decide when to act and activating a reasoner only when needed, achieving reduced false trigger rates and improved success rates and inference efficiency on the ProactiveMobile benchmark.
Multimodal large language models (MLLMs) have substantially advanced mobile agents, yet proactive mobile assistance remains challenging because agents must decide \emph{when} to intervene before determining \emph{how} to assist. Existing systems often implement these two decisions within a unified MLLM-based pipeline, leading to goal misalignment between conservative intervention filtering and comprehensive assistance generation, as well as redundant inference when the agent should remain silent. To address these limitations, we propose the \textbf{Pre-Reasoning Perception Framework (PRPF)}, a two-stage framework built on perceiving before reasoning. PRPF introduces a lightweight Multimodal Proactive Perceptor (MPP) for intervention gating and context compression, and activates the Proactive Agent Reasoner (PAR) only when intervention is warranted. Experiments on the ProactiveMobile benchmark show that PRPF substantially reduces false trigger rates (FTR) while improving success rates (SR) and inference efficiency over the ProactiveMobile baseline.