EverMind AI 开源多智能体系统 Raven：为每个模型单独演化 harness
EverMind AI 开源了 Raven，每个模型配一套会自我进化的 harness，用 DeepSeek-V4-Flash 在 BrowseComp 上跑出 69.3%，研究者可以看看这套思路。
EverMind AI 发布开源多智能体系统 Raven，为每个模型和领域单独构建 harness，由 host agent 将目标拆成任务图并分发到 model-harness 对。harness 组件会被诊断、变异和重组，候选方案需通过统计检验才能替换现有版本。使用 DeepSeek-V4-Flash 时，research harness 在 BrowseComp 上得 69.3%、在 Humanity's Last Exam 上得 60.0%，而同模型下另外两个 harness 最高只有 62.4% 和 43.3%。其精选技能库将 SkillsBench Pass@1 从无技能时的 9.2% 提升到 22.6%。
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: https://t.co/FGWHgSug42
Chat with Paper: https://t.co/BsNe1SGsPr
