Quine: Realizing LLM Agents as Native POSIX Processes
This addresses inefficiencies in LLM agent orchestration for developers by leveraging existing OS mechanisms, though it is incremental in building on standard process models.
The paper tackles the problem of LLM agent frameworks implementing isolation and communication at the application layer by introducing Quine, a runtime architecture that maps LLM agents to native POSIX processes, inheriting kernel-level isolation and resource control.
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.