发表机构
EverMind AI（EverMind AI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Raven是一个开源多智能体生态系统，通过自动构建和演化模块化驾驭，将模型-驾驭对作为可组合单元，实现跨领域长时程任务的自主编排，并显著超越现有最先进系统。
AI 中文摘要
随着大语言模型的进步，AI智能体正从孤立的、特定领域的任务转向长时程、跨领域的工作流。这一转变暴露了两个挑战：日益复杂的驾驭（harness）设计使得手动设计难以扩展，而对特定领域的更紧密耦合则限制了单一驾驭的通用性。因此，核心问题从如何为一个领域设计更强的驾驭，转变为如何自主构建专门的驾驭、通过经验改进它们，并在各领域间进行编排。我们提出Raven，即“驾驭之驾驭”，一个开源的多智能体生态系统，它自动为特定模型和领域构建并演化模块化驾驭，将每个可执行的模型-驾驭对视为一个可组合的智能单元。为支持“全领域协作网络”，其宿主智能体（Host Agent）分解目标、将子任务匹配给专门智能体、协调执行依赖并整合结果，同时宿主档案库和EverOS跨任务保留经验，而Skill Forge将这些经验作为可复用过程提供。我们的理论建立了充分条件，使得在共享资源预算下，这种组合能扩展可靠任务覆盖范围，超越现有单个智能体所能达到的范围。在复杂和长时程任务上，Raven显著优于最先进的智能体系统，推动了可组合智能体智能的前沿。
英文摘要
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 to how to autonomously construct specialized harnesses, improve them through experience, and orchestrate them across domains. We introduce Raven, \emph{The Harness of Harnesses}, an open-source multi-agent ecosystem that automatically constructs and evolves modular harnesses for specific models and domains, treating each executable model--harness pair as a composable unit of intelligence. To support an \emph{All-Domain Collaboration Network}, its Host Agent decomposes goals, matches subtasks to specialized agents, coordinates execution dependencies, and integrates results, while a host archive and EverOS preserve experience across tasks and Skill Forge makes that experience available as reusable procedures. Our theory establishes sufficient conditions for such composition to expand reliable task coverage beyond that of the available individual agents under a shared resource budget. On complex and long-horizon tasks, Raven significantly outperforms the state-of-the-art agent systems, pushing the frontier of composable agentic intelligence.
