FrontierChallenge: Evaluating Scientific Workflow Completion Paper • 2608.24979 • Published 3 days ago • 137
Apodex 1.1: Scaling Agentic Intelligence for Complex Work Paper • 2608.23283 • Published 4 days ago • 197
MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification Paper • 2603.15726 • Published Mar 16 • 187