Iris search agents hit open-source SOTA via SFT-RL climbing at 35B and 397B scales

_reachsumit · x · 2026-09-07

Researchers released Iris-mini and Iris-pro, open-source search agents trained at 35B-A3B and 397B-A17B scales, claiming SOTA among open search agents.

Key method:

Evaluation: the paper stresses that inference-time context management matters more than most reported system differences, so every benchmark is evaluated with and without it; results come from a single ReAct agent with no sub-agents or test-time verification.

Related event: Iris: Open-Source Search Agents Hit New SOTA(2 posts)→

Original post →

More from Research

Research channel →