DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents
cs.AI
Submitted: 2026-10-08
Updated: 2026-10-08
Sources
- Qwen3-VL Technical Report
- UI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI Agents
- Get Experience from Practice: LLM Agents with Record & Replay
- AppAgentX: Evolving GUI Agents as Proficient Smartphone Users
- SE-GA: Memory-Augmented Self-Evolution for GUI Agents
- MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automation
- AppAgent v2: Advanced Agent for Flexible Mobile Interactions
- MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments
- Beyond Training: Enabling Self-Evolution of Agents with MOBIMEM
- Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- Executable Agentic Memory for GUI Agent
- Enhancing Web Agents with a Hierarchical Memory Tree
- Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
- Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks
- UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agents
- Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
- Corrective Retrieval Augmented Generation
- Mem-W: Latent Memory-Native GUI Agents
- FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory
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
- Agents' Last Exam
- 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