Iris pushes open search agents past the context-management bottleneck
Search agents often lose the plot before they find the answer. Iris attacks that failure directly: its training pipeline builds deliberately hard multi-hop questions, filters trajectories turn by turn, and trains the policy with live search plus resumable context management. Iris-mini and Iris-pro report 82.2 to 92.9% across BrowseComp, BrowseComp-ZH, and DeepSearchQA, with up to 56.4% on HLE. The notable result is not just scale, but a recipe others can reproduce.