FrontierChallenge: Evaluating Scientific Workflow Completion Paper • 2608.24979 • Published about 1 month ago • 152
Apodex 1.1: Scaling Agentic Intelligence for Complex Work Paper • 2608.23283 • Published Aug 24 • 210
DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment Paper • 2607.07820 • Published Jul 8 • 95