WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces Paper • 2606.09426 • Published 9 days ago • 100
InterleaveThinker: Reinforcing Agentic Interleaved Generation Paper • 2606.13679 • Published 6 days ago • 78
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Paper • 2606.11926 • Published 7 days ago • 110
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published 20 days ago • 193
electricsheepasia/asia-owid-armed-forces-personnel-percent Viewer • Updated 14 days ago • 1.45k • 87 • 1
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security Paper • 2605.29801 • Published 20 days ago • 142
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 21 days ago • 423
Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints Paper • 2605.21085 • Published 28 days ago • 5