Raven：面向可组合智能体的 Harness 之 Harness
原标题：Paper page - Raven: The Harness of Harnesses for Composable Agentic Intelligence
AI 摘要
该论文提出 Raven，一个开源多智能体生态系统，可自动为特定模型和领域构建并演化模块化 harness，将每个可执行的模型-harness 对视为可组合的智能单元。其 Host Agent 负责任务分解、子任务匹配、执行依赖协调与结果整合，配合 host archive、EverOS 和 Skill Forge 实现跨任务经验保留与复用。论文给出组合扩展可靠任务覆盖的理论充分条件，并称 Raven 在复杂长时程任务上显著优于现有最先进智能体系统。
正文节选
Raven: The Harness of Harnesses for Composable Agentic Intelligence Abstract As large language models advance, AI agents are moving beyond isolated, domain-specific tasks toward long-horizon, cross-domain workflows. This transition exposes two challenges: increasing harness complexity makes manual design difficult to scale, while tighter coupling to specific domains limits the generality of a single harness. The central question thus shifts from how to engineer a stronger harness for one domain