MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models
cs.AI
Submitted: 2026-06-03
Updated: 2026-11-07
Code: https://github.com/yzc0912/MIRAGE
Terminology
Sources
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- MAI-UI Technical Report: Real-World Centric Foundation GUI Agents
- OS-ATLAS: A Foundation Action Model for Generalist GUI Agents
- AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
- Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
- ReAct: Synergizing Reasoning and Acting in Language Models
- Think before you speak: Training Language Models With Pause Tokens
- Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
- Implicit Chain of Thought Reasoning via Knowledge Distillation
- Training Large Language Models to Reason in a Continuous Latent Space
- World Models
- Dream to Control: Learning Behaviors by Latent Imagination
- Revisiting Feature Prediction for Learning Visual Representations from Video
- TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks
- ViMo: A Generative Visual GUI World Model for App Agents
- MobileDreamer: Generative Sketch World Model for GUI Agent
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- Qwen3-VL Technical Report
- GPT-4o System Card
- GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents