Iris: Climbing to the Search Frontier
Two open search agents (35B-A3B and 397B-A17B) trained with an SFT-RL alternation over multi-hop questions built from web hyperlink structure, where no clue is resolvable by string matching. With context management enabled, Iris-pro scores 88.6 on BrowseComp and 56.4 on HLE, claimed best among open-source search agents in their parameter ranges; weights and the full recipe are promised for release.
Why it matters
BrowseComp-level search has been an open-weight gap; a reported 88.6 with a full data-plus-training recipe release would make deep-search agents reproducible outside closed labs. 50 upvotes on HF Daily Papers.
Importance: 3/5
Strongest open-weight BrowseComp results to date with a promised full recipe; 50 HF Daily upvotes