StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents Paper • 2607.22798 • Published 5 days ago • 51
GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse Paper • 2401.01523 • Published Jan 3, 2024 • 2
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism Paper • 2606.00408 • Published May 29 • 65
MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers Paper • 2508.14704 • Published Aug 20, 2025 • 43