EverMind AI 开源多智能体系统 Raven
EverMind AI 发布开源多智能体系统 Raven，它为每个模型和领域构建独立 harness，由 host agent 将目标拆解为任务图并分发给各模型-harness 组合，harness 组件经诊断、变异与重组后需通过统计检验才能替换现有版本。
Huge release from EverMind AI.
Raven is an open-source multi-agent system that builds a separate harness for each model and domain, evolves those harnesses from their failures, and coordinates them through a host agent.
The host agent splits a goal into a task graph and sends 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.
With 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%.
Paper: arxiv.org/abs/2609.33439
Chat with Paper: academy.dair.ai/papers/raven…
来源：dair_ai · x.com