DAIR.AI describes Raven, EverMind AI’s open-source multi-agent system that builds a separate harness for each model and domain and evolves it from failures. With DeepSeek-V4-Flash, its research harness scores 69.3% on BrowseComp and 60.0% on Humanity's Last Exam.
DAIR.AI describes ActiveSaddler, a paper from Microsoft and colleagues that changes which scenarios are used to optimize an agent harness. With the same optimizer, test Pass@1 improves by 4.4 points on GAIA2 and 7.5 points on Terminal-Bench 2.0 versus a fixed scenario order.
A paper from Google and colleagues describes Harness-Zero, which uses an optimized agent harness only during training. After that harness is removed, macro task success rises from 23.3% to 44.3%, above the 41.7% reached by the base model with the harness attached.
