MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments Paper • 2602.06075 • Published 15 days ago • 13
AgentOCR: Reimagining Agent History via Optical Self-Compression Paper • 2601.04786 • Published Jan 8 • 29
OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents Paper • 2510.24563 • Published Oct 28, 2025 • 23