AgentOCR: Reimagining Agent History via Optical Self-Compression Paper • 2601.04786 • Published 26 days ago • 29
AgentOCR: Reimagining Agent History via Optical Self-Compression Paper • 2601.04786 • Published 26 days ago • 29
QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management Paper • 2512.12967 • Published Dec 15, 2025 • 108
OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents Paper • 2510.24563 • Published Oct 28, 2025 • 23
OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents Paper • 2510.24563 • Published Oct 28, 2025 • 23
UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning Paper • 2509.11543 • Published Sep 15, 2025 • 49
UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning Paper • 2509.11543 • Published Sep 15, 2025 • 49
UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning Paper • 2509.11543 • Published Sep 15, 2025 • 49 • 3
Mobile-Agent-v3: Foundamental Agents for GUI Automation Paper • 2508.15144 • Published Aug 21, 2025 • 64
Mobile-Agent-v3: Foundamental Agents for GUI Automation Paper • 2508.15144 • Published Aug 21, 2025 • 64
Mobile-Agent-v3: Foundamental Agents for GUI Automation Paper • 2508.15144 • Published Aug 21, 2025 • 64 • 3
Perception-Aware Policy Optimization for Multimodal Reasoning Paper • 2507.06448 • Published Jul 8, 2025 • 48
Perception-Aware Policy Optimization for Multimodal Reasoning Paper • 2507.06448 • Published Jul 8, 2025 • 48