arXiv:2603.18030cs.OScs.AI2026-03被引 1

让大模型代理成为操作系统原生进程,提升隔离与调度能力

Quine: Realizing LLM Agents as Native POSIX Processes

  • 将LLM代理映射为原生POSIX进程,用PID、标准流等实现身份与通信
  • 继承操作系统内核的隔离与资源控制,支持递归调用和环境重置
  • 适合需要高安全性和系统级集成的AI应用开发者

当前LLM代理框架常在应用层实现隔离、调度与通信,尽管这些功能已由成熟操作系统提供。本文提出Quine,一种将LLM代理作为原生POSIX进程运行的架构与参考实现。该设计明确映射:身份为进程ID(PID),接口为标准输入输出流与退出状态,状态包括内存、环境变量与文件系统,生命周期由fork/exec/exit管理。单一可执行文件通过递归自启动实现此模型。通过基于操作系统进程模型,Quine直接继承内核提供的隔离性、组合性与资源控制,自然支持递归委托、通过exec实现上下文刷新及壳命令原生组合。分析也揭示了进程模型的局限:虽提供可靠执行基础,但非完整认知运行时。研究指出两个即时扩展方向:任务相关世界与可回溯时间。Quine的参考实现已公开于GitHub。

原文摘要 · Abstract (English)

Current LLM agent frameworks often implement isolation, scheduling, and communication at the application layer, even though these mechanisms are already provided by mature operating systems. Instead of introducing another application-layer orchestrator, this paper presents Quine, a runtime architecture and reference implementation that realizes LLM agents as native POSIX processes. The mapping is explicit: identity is PID, interface is standard streams and exit status, state is memory, environment variables, and filesystem, and lifecycle is fork/exec/exit. A single executable implements this model by recursively spawning fresh instances of itself. By grounding the agent abstraction in the OS process model, Quine inherits isolation, composition, and resource control directly from the kernel, while naturally supporting recursive delegation, context renewal via exec, and shell-native composition. The design also exposes where the POSIX process model stops: processes provide a robust substrate for execution, but not a complete runtime model for cognition. In particular, the analysis points toward two immediate extensions beyond process semantics: task-relative worlds and revisable time. A reference implementation of Quine is publicly available on GitHub.

LLM代理操作系统进程模型运行时

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。