EverMind AI releases Raven, an open-source system that evolves model harnesses

Raven uses a host agent to split a goal into a task graph and send each part to a model-harness pair for research, code, design, or on-call work. Harness components are diagnosed, mutated, and recombined, and a candidate replaces the current harness only after passing a statistical check.

DAIR.AI reports that, on DeepSeek-V4-Flash, the research harness scores 69.3% on BrowseComp and 60.0% on Humanity's Last Exam, against at most 62.4% and 43.3% for two other harnesses on the same model. Its curated skill library raises SkillsBench Pass@1 from 9.2% with no skills to 22.6%. The paper is [Raven: The Harness of Harnesses for Composable Agentic Intelligence](https://arxiv.org/abs/2609.33439).