发表机构
Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出人类-AI共存概念，设计实现CrabOS操作系统，以共享文本对象为工作状态，实现人类与AI无缝交替主导任务，为AI智能体开发运行提供新基础。
AI 中文摘要
AI智能体正在演变为可长期运行的计算实体，能够调用工具、维护内存并跨应用完成复杂任务。在现实场景中，完成一项任务往往需要人类与AI交替主导执行，这种交替依赖于任务工作状态在人类与AI之间的无缝交接。然而，现有的智能体系统为人类和AI提供了独立的工作环境，AI智能体必须依赖额外的桥梁才能继续工作：要么开发者构建特定任务的接口以访问工作状态，要么用户通过截图或文本描述手动传输相关部分。两种方式都导致交接成本高昂且扩展性差。我们提出人类-AI共存（Human-AI Co-inhabitation），这是一种使人类和AI能够无缝交替主导同一任务工作的环境，并设计实现了CrabOS来实现这一概念。CrabOS将工作状态表示为人类与AI共享的自然语言可读文本对象，允许双方通过同一可审计接口直接访问和操作，无需桥梁。案例研究表明，CrabOS将对人类与AI交替主导的复杂任务的支持，从依赖桥梁的应用级解决方案提升为原生操作系统级功能，为开发和运行AI智能体提供了新基础。
英文摘要
AI agents are evolving into long-running computational entities that can invoke tools, maintain memory, and complete complex tasks across applications. In real-world settings, completing a task often requires humans and AI to take turns leading its execution. Such alternation depends on the seamless handoff of the work state of the task between humans and AI. Existing agent systems, however, provide humans and AI with separate work environments. AI agents must therefore rely on additional bridges to continue work: either developers build task-specific interfaces to access the work state, or users manually transfer relevant parts of it through screenshots or textual descriptions. Both approaches make handoffs costly and scale poorly. We propose Human-AI Co-inhabitation, a type of work environment that enables humans and AI to seamlessly take turns continuing work on the same task, and design and implement CrabOS to realize this concept. CrabOS represents the work state as natural-language-readable text objects shared by humans and AI, allowing both to access and manipulate it directly through the same auditable interface without bridges. Case studies show that CrabOS elevates support for complex tasks with alternating human and AI leadership from bridge-dependent application-level solutions to native operating-system capabilities, which provide a new foundation for developing and running AI agents.
