Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents

arXiv:2606.03236 · cs.AI · Submitted 2026-06-02 · Read on arXiv

cs.AI

Submitted: 2026-06-02

Updated: 2026-08-31

Terminology

• GRPO — 18× in this paper · explained in 6 episodes
• Benchmark — 16× in this paper · explained in 2 episodes
• Accuracy — 15× in this paper · explained in 1 episode
• Grounding — 11× in this paper · explained in 3 episodes
• Proactive Agent Reasoner — 6× in this paper
• Ablation — 5× in this paper · explained in 1 episode
• Aggregation — 4× in this paper · explained in 1 episode
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Multimodal Proactive Perceptor — 4× in this paper
• Pre-Reasoning Perception Framework — 4× in this paper
• Adam — 3× in this paper · explained in 2 episodes
• Calibration — 3× in this paper · explained in 7 episodes
• Core — 3× in this paper · explained in 2 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Abstention — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Modality Gap — 2× in this paper · explained in 4 episodes
• Multimodal Fusion — 2× in this paper · explained in 3 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Two-Stage Framework — 2× in this paper · explained in 2 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Error Decomposition — 1× in this paper · explained in 3 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• PRISM: Festina Lente Proactivity -- Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agents
• GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
• GPT-4o System Card
• Kimi K2.5: Visual Agentic Intelligence
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices
• Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems
• DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding
• ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data
• BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models
• Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
• iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perception
• Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Tasks
• Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
• RouteLLM: Learning to Route LLMs with Preference Data
• PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
• ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection